Triple

T200641
Position Surface form Disambiguated ID Type / Status
Subject Austronesian languages E4098 entity
Predicate hasSubfamily P747 FINISHED
Object South Halmahera–West New Guinea languages
The South Halmahera–West New Guinea languages are a subgroup of Austronesian languages spoken in eastern Indonesia and western New Guinea, notable for their geographic isolation and distinctive phonological and grammatical features.
 E4098 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: South Halmahera–West New Guinea languages | Statement: [Austronesian languages, hasSubfamily, South Halmahera–West New Guinea languages]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: South Halmahera–West New Guinea languages
Context triple: [Austronesian languages, hasSubfamily, South Halmahera–West New Guinea languages]
  • A. Penutian languages
    Penutian languages are a proposed family of Native American languages spoken primarily in the western United States, noted for their controversial genetic relationships and inclusion of several distinct regional language groups.
  • B. Austronesian languages
    Austronesian languages are a large and widely dispersed language family spoken across maritime Southeast Asia, Madagascar, the Pacific Islands, and parts of mainland Asia.
  • C. Philippine–Cordilleran languages
    The Philippine–Cordilleran languages are a major subgroup of the Austronesian language family spoken primarily in the northern Philippines, encompassing numerous indigenous languages of the Cordillera region and surrounding areas.
  • D. Ryukyuan languages
    The Ryukyuan languages are a group of closely related but distinct Japonic languages traditionally spoken in Japan’s Ryukyu Islands, many of which are now endangered.
  • E. Solomon Islands Pijin
    Solomon Islands Pijin is an English-based creole language widely used as a lingua franca across the Solomon Islands.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: South Halmahera–West New Guinea languages
Triple: [Austronesian languages, hasSubfamily, South Halmahera–West New Guinea languages]
Generated description
The South Halmahera–West New Guinea languages are a subgroup of Austronesian languages spoken in eastern Indonesia and western New Guinea, notable for their geographic isolation and distinctive phonological and grammatical features.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: South Halmahera–West New Guinea languages
Target entity description: The South Halmahera–West New Guinea languages are a subgroup of Austronesian languages spoken in eastern Indonesia and western New Guinea, notable for their geographic isolation and distinctive phonological and grammatical features.
  • A. Penutian languages
    Penutian languages are a proposed family of Native American languages spoken primarily in the western United States, noted for their controversial genetic relationships and inclusion of several distinct regional language groups.
  • B. Austronesian languages chosen
    Austronesian languages are a large and widely dispersed language family spoken across maritime Southeast Asia, Madagascar, the Pacific Islands, and parts of mainland Asia.
  • C. Philippine–Cordilleran languages
    The Philippine–Cordilleran languages are a major subgroup of the Austronesian language family spoken primarily in the northern Philippines, encompassing numerous indigenous languages of the Cordillera region and surrounding areas.
  • D. Ryukyuan languages
    The Ryukyuan languages are a group of closely related but distinct Japonic languages traditionally spoken in Japan’s Ryukyu Islands, many of which are now endangered.
  • E. Solomon Islands Pijin
    Solomon Islands Pijin is an English-based creole language widely used as a lingua franca across the Solomon Islands.
  • F. None of above.

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69a254bca59881909a15e1496f1508c7 completed Feb. 28, 2026, 2:36 a.m.
NER Named-entity recognition batch_69a25be47ea881909c296b30a0d47a65 completed Feb. 28, 2026, 3:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69a32bc5d56c8190bbe922eee86bcc58 completed Feb. 28, 2026, 5:54 p.m.
NEDg Description generation batch_69a32c3933988190b570bcd442b7095e completed Feb. 28, 2026, 5:56 p.m.
NED2 Entity disambiguation (via description) batch_69a32cbc7db08190a94e1ac4d35ca257 completed Feb. 28, 2026, 5:58 p.m.
Created at: Feb. 28, 2026, 2:44 a.m.