Triple

T21820391
Position Surface form Disambiguated ID Type / Status
Subject Ambaji Temple E538709 entity
Predicate locatedIn P40 FINISHED
Object Ambaji 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: Ambaji | Statement: [Ambaji Temple, locatedIn, Ambaji]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ambaji
Context triple: [Ambaji Temple, locatedIn, Ambaji]
  • A. Ambaji chosen
    Ambaji is a revered form of the Hindu goddess Shakti, worshipped as a principal manifestation of the Divine Mother in western India.
  • B. Awabagal
    Awabagal is an alternative name for the Awabakal language, an Indigenous Australian language traditionally spoken by the Awabakal people of the coastal New South Wales region.
  • C. Abijo
    Abijo is a suburban community in the Lekki area of Lagos State, Nigeria, situated along the Lekki–Epe development corridor.
  • D. Abur
    Abur is the traditional name for the Old Permic alphabet, an early writing system used for the Komi language in the medieval Perm region of Russia.
  • E. Abae
    Abae was an ancient town in Phocis, Greece, best known for its important oracle of Apollo and its role in various Greek historical and religious events.
  • 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_69e0c475038c8190abb9b1a20eb8ff50 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f0912d414c81909c109c3e45b6e7d2 completed April 28, 2026, 10:51 a.m.
Created at: April 16, 2026, 6:54 p.m.