Triple

T7840823
Position Surface form Disambiguated ID Type / Status
Subject Western Oceanic E181797 entity
Predicate hasLanguage P15 FINISHED
Object Suau
Suau is an Oceanic language spoken by communities in southeastern Papua New Guinea, particularly in Milne Bay Province.
 E696164 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: Suau | Statement: [Western Oceanic, hasLanguage, Suau]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Suau
Context triple: [Western Oceanic, hasLanguage, Suau]
  • A. Suawa
    Suawa is an Austronesian language spoken by the Suwawa people of North Sulawesi, Indonesia.
  • B. Sulmo
    Sulmo is an ancient town in central Italy, historically known as the birthplace of the Roman poet Ovid.
  • C. Sioule
    The Sioule is a river in central France that flows through the Auvergne region before joining the Allier River.
  • D. Savu
    Savu is a small Indonesian island in the Lesser Sunda chain, known for its traditional culture, dry climate, and location between Sumba and Timor.
  • E. Ouakam
    Ouakam is a coastal district of Dakar, Senegal, known for its historic fishing community, military installations, and prominent location beneath the African Renaissance Monument.
  • 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: Suau
Triple: [Western Oceanic, hasLanguage, Suau]
Generated description
Suau is an Oceanic language spoken by communities in southeastern Papua New Guinea, particularly in Milne Bay Province.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Suau
Target entity description: Suau is an Oceanic language spoken by communities in southeastern Papua New Guinea, particularly in Milne Bay Province.
  • A. Suawa
    Suawa is an Austronesian language spoken by the Suwawa people of North Sulawesi, Indonesia.
  • B. Sulmo
    Sulmo is an ancient town in central Italy, historically known as the birthplace of the Roman poet Ovid.
  • C. Sioule
    The Sioule is a river in central France that flows through the Auvergne region before joining the Allier River.
  • D. Savu
    Savu is a small Indonesian island in the Lesser Sunda chain, known for its traditional culture, dry climate, and location between Sumba and Timor.
  • E. Ouakam
    Ouakam is a coastal district of Dakar, Senegal, known for its historic fishing community, military installations, and prominent location beneath the African Renaissance Monument.
  • 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_69ca8285d6488190a95d4c02d7354b53 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb14c589748190b34d0911d373e194 completed March 31, 2026, 12:26 a.m.
NED1 Entity disambiguation (via context triple) batch_69cb5aca5e348190bb73fc4748093248 completed March 31, 2026, 5:25 a.m.
NEDg Description generation batch_69cb5def38e88190864d84abd7959aa3 completed March 31, 2026, 5:38 a.m.
NED2 Entity disambiguation (via description) batch_69cb765db28881909ac34071ec6889b3 completed March 31, 2026, 7:23 a.m.
Created at: March 30, 2026, 4:47 p.m.