Triple

T19017985
Position Surface form Disambiguated ID Type / Status
Subject Kerkebet E465405 entity
Predicate regionCapital P16248 FINISHED
Object Keren 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: Keren | Statement: [Kerkebet, regionCapital, Keren]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Keren
Context triple: [Kerkebet, regionCapital, Keren]
  • A. Keren chosen
    Keren is a major town in Eritrea known as an important commercial and agricultural center in the Anseba region.
  • B. Keren Rosenberg
    Keren Rosenberg is a film producer known for her work on the adaptation of Amos Oz’s autobiographical novel "A Tale of Love and Darkness."
  • C. Sharona Katan
    Sharona Katan is an Israeli-born visual artist and the wife of Radiohead guitarist and composer Jonny Greenwood.
  • D. Saar Ganor
    Saar Ganor is an Israeli archaeologist known for directing major excavations at key biblical-era sites, including the fortified city of Tel Qeiyafa.
  • E. Keira Hagai
    Keira Hagai is a skilled mechanic and hovercraft engineer who serves as Jak’s close ally and love interest in the Jak and Daxter video game series.
  • 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_69d8dd025c188190a1d81f5b4ec7e2c6 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d6dd0e6c8190a6dc6af1f7901299 completed April 20, 2026, 7:33 a.m.
Created at: April 10, 2026, 12:02 p.m.