Triple

T14301602
Position Surface form Disambiguated ID Type / Status
Subject Pentecost Island E354576 entity
Predicate hasLanguage P15 FINISHED
Object Sowa language
Sowa language is an Oceanic language traditionally spoken by a small community on Pentecost Island in Vanuatu.
 E1091507 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: Sowa language | Statement: [Pentecost Island, hasLanguage, Sowa language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sowa language
Context triple: [Pentecost Island, hasLanguage, Sowa language]
  • A. Sa’och language
    The Sa’och language is an endangered Austroasiatic language spoken by the Sa’och people of Cambodia and Thailand, belonging to the Pearic branch.
  • B. Suwawa language
    The Suwawa language is an Austronesian language spoken by the Suwawa people of northern Sulawesi, Indonesia, and is part of the Gorontalo–Mongondow subgroup.
  • C. Soga language
    The Soga language is a Bantu language spoken primarily by the Basoga people in eastern Uganda.
  • D. Bafia language
    The Bafia language is a Bantu language spoken primarily by the Bafia people in central Cameroon.
  • E. Saho language
    The Saho language is an Afroasiatic Cushitic language spoken primarily by the Saho people in Eritrea and northern Ethiopia.
  • 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: Sowa language
Triple: [Pentecost Island, hasLanguage, Sowa language]
Generated description
Sowa language is an Oceanic language traditionally spoken by a small community on Pentecost Island in Vanuatu.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sowa language
Target entity description: Sowa language is an Oceanic language traditionally spoken by a small community on Pentecost Island in Vanuatu.
  • A. Sa’och language
    The Sa’och language is an endangered Austroasiatic language spoken by the Sa’och people of Cambodia and Thailand, belonging to the Pearic branch.
  • B. Suwawa language
    The Suwawa language is an Austronesian language spoken by the Suwawa people of northern Sulawesi, Indonesia, and is part of the Gorontalo–Mongondow subgroup.
  • C. Soga language
    The Soga language is a Bantu language spoken primarily by the Basoga people in eastern Uganda.
  • D. Bafia language
    The Bafia language is a Bantu language spoken primarily by the Bafia people in central Cameroon.
  • E. Saho language
    The Saho language is an Afroasiatic Cushitic language spoken primarily by the Saho people in Eritrea and northern Ethiopia.
  • 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_69d8278e17088190b328c5a9d4be74ff completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de717fc2348190bb6ba3109bd2871f completed April 14, 2026, 4:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd3d2883e081909c53170ef30b4125 completed May 8, 2026, 1:32 a.m.
NEDg Description generation batch_69fd3dc46b408190b7c515156f81f1fc completed May 8, 2026, 1:35 a.m.
NED2 Entity disambiguation (via description) batch_69fd3eb045488190b44812eb638807ff completed May 8, 2026, 1:38 a.m.
Created at: April 10, 2026, 1:11 a.m.