Triple

T1027276
Position Surface form Disambiguated ID Type / Status
Subject Bali E22167 entity
Predicate localLanguage P1252 FINISHED
Object Sasak
Sasak is an Austronesian language spoken primarily by the Sasak people on the Indonesian island of Lombok.
 E119554 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: Sasak | Statement: [Bali, localLanguage, Sasak]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sasak
Context triple: [Bali, localLanguage, Sasak]
  • A. Sumbawa
    Sumbawa is an island in central Indonesia, part of the Lesser Sunda Islands, known for its volcanic landscapes, surfing spots, and relatively low population density compared to neighboring Bali and Lombok.
  • B. Bantia
    Bantia was an ancient Oscan-speaking city in southern Italy, notable for yielding important inscriptions that illuminate the Oscan language and Italic legal traditions.
  • C. Kuta Lombok
    Kuta Lombok is a coastal town on the Indonesian island of Lombok known for its scenic white-sand beaches, surf breaks, and laid-back tourism atmosphere.
  • D. Sumba
    Sumba is a rugged island in eastern Indonesia known for its traditional Marapu culture, megalithic tombs, and distinctive ikat textiles.
  • E. Ranggawuni
    Ranggawuni was a 13th-century Javanese king of the Singhasari Kingdom, known for consolidating royal power and laying groundwork for the rise of later Javanese empires.
  • 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: Sasak
Triple: [Bali, localLanguage, Sasak]
Generated description
Sasak is an Austronesian language spoken primarily by the Sasak people on the Indonesian island of Lombok.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sasak
Target entity description: Sasak is an Austronesian language spoken primarily by the Sasak people on the Indonesian island of Lombok.
  • A. Sumbawa
    Sumbawa is an island in central Indonesia, part of the Lesser Sunda Islands, known for its volcanic landscapes, surfing spots, and relatively low population density compared to neighboring Bali and Lombok.
  • B. Bantia
    Bantia was an ancient Oscan-speaking city in southern Italy, notable for yielding important inscriptions that illuminate the Oscan language and Italic legal traditions.
  • C. Kuta Lombok
    Kuta Lombok is a coastal town on the Indonesian island of Lombok known for its scenic white-sand beaches, surf breaks, and laid-back tourism atmosphere.
  • D. Sumba
    Sumba is a rugged island in eastern Indonesia known for its traditional Marapu culture, megalithic tombs, and distinctive ikat textiles.
  • E. Ranggawuni
    Ranggawuni was a 13th-century Javanese king of the Singhasari Kingdom, known for consolidating royal power and laying groundwork for the rise of later Javanese empires.
  • F. None of above. chosen

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_69a493d6e380819097b384986ffc315c completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b7f6ff048190863f9c38162d09b7 completed March 1, 2026, 10:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac3bbce0b88190b91380fca297cd38 completed March 7, 2026, 2:52 p.m.
NEDg Description generation batch_69ac3cd7e87481909313eef251654654 completed March 7, 2026, 2:57 p.m.
NED2 Entity disambiguation (via description) batch_69ac3d3ed140819087ede15c555e2f4d completed March 7, 2026, 2:59 p.m.
Created at: March 1, 2026, 7:41 p.m.