Triple

T15802748
Position Surface form Disambiguated ID Type / Status
Subject Og, king of Bashan E383135 entity
Predicate kingdomRegion P64798 FINISHED
Object Bashan E383136 NE FINISHED

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: Bashan | Statement: [Og, king of Bashan, kingdomRegion, Bashan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bashan
Context triple: [Og, king of Bashan, kingdomRegion, Bashan]
  • A. Bashan chosen
    Bashan is a historically significant region east of the Jordan River, renowned in biblical texts for its fertile lands, strong cities, and mighty cattle.
  • B. Shemshak
    Shemshak is a mountain village and ski resort in the Alborz range of northern Iran, known for its steep slopes and popularity among advanced skiers.
  • C. Shushan
    Shushan is the ancient Persian royal city traditionally identified as the capital where the events of the biblical Book of Esther take place.
  • D. Bakhah
    Bakhah is a village in Syria known as one of the few remaining communities where Western Neo-Aramaic is still actively spoken.
  • E. Giabal
    Giabal are an Aboriginal Australian people traditionally associated with the Darling Downs region of southern Queensland.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d86da16e188190b89af699f1ed0bfe completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e142e0e1cc8190851b30b03cf9c9b8 completed April 16, 2026, 8:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69ff998b52e481908baa20b5a8c1cbcf completed May 9, 2026, 8:31 p.m.
Created at: April 10, 2026, 4:48 a.m.