Triple

T19775849
Position Surface form Disambiguated ID Type / Status
Subject Zeruiah E474999 entity
Predicate motherOf P120 FINISHED
Object Abishai 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: Abishai | Statement: [Zeruiah, motherOf, Abishai]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Abishai
Context triple: [Zeruiah, motherOf, Abishai]
  • A. Abishai chosen
    Abishai is a prominent Old Testament military leader and nephew of King David, known for his close association with his brother Joab and his role in David’s campaigns.
  • B. Joab
    Joab is a prominent military commander in the Hebrew Bible, known especially as King David’s ruthless yet loyal army leader.
  • C. Benaiah
    Benaiah was a prominent Israelite warrior and commander under King David and King Solomon, renowned for his bravery and loyalty in biblical accounts.
  • D. Shaul
    Shaul is the Hebrew form of the name Saul, most famously associated with the first king of ancient Israel in the Hebrew Bible.
  • E. Jonadab
    Jonadab is a shrewd but morally dubious cousin of Amnon in the biblical narrative, known for advising Amnon in his plot against Tamar and later revealing knowledge of Absalom’s revenge.
  • 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_69d8e51a43a08190956bc6df13c91a77 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6535fb114819089911ed3ba6565c0 completed April 20, 2026, 4:25 p.m.
Created at: April 10, 2026, 1:48 p.m.