Triple

T22933836
Position Surface form Disambiguated ID Type / Status
Subject Balantak E569518 entity
Predicate languageFamily P1047 FINISHED
Object Celebic NE NERFINISHED

How this triple was built (2 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: Celebic | Statement: [Balantak, languageFamily, Celebic]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Celebic
Context triple: [Balantak, languageFamily, Celebic]
  • A. Celebic chosen
    Celebic is a major subgroup of the Austronesian language family comprising numerous related languages spoken primarily on the Indonesian island of Sulawesi.
  • B. Bélesta
    Bélesta is a small commune in the Ariège department of southwestern France, known for its scenic Pyrenean foothills and nearby prehistoric caves.
  • C. Berjallien
    A Berjallien is a resident or native of Bourgoin-Jallieu, a town in the Isère department of southeastern France.
  • D. Balice
    Balice is a village near Kraków in southern Poland, best known for hosting the region’s main international airport.
  • E. Corabia
    Corabia is a small town in southern Romania, situated on the Danube River in Olt County and known historically as a local port and agricultural center.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e24590862c8190858f180ad302adab completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18134484c8190b7311606c17d058d completed April 29, 2026, 3:55 a.m.
Created at: April 17, 2026, 3:44 p.m.