Triple

T5373340
Position Surface form Disambiguated ID Type / Status
Subject Amalekites E108902 entity
Predicate opponentInBattle P3861 FINISHED
Object Saul E109473 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: Saul | Statement: [Amalekites, opponentInBattle, Saul]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Saul
Context triple: [Amalekites, opponentInBattle, Saul]
  • A. Saul
    Saul is a surname most notably associated with Canadian philosopher and writer John Ralston Saul.
  • B. Saul chosen
    Saul is the first king of Israel in the Hebrew Bible, known for his tumultuous reign and complex relationship with the prophet Samuel and his successor David.
  • C. Jonathan son of Saul
    Jonathan son of Saul was a valiant Israelite prince and close friend of David, renowned for his loyalty, courage in battle, and tragic death fighting the Philistines.
  • D. Zamani Saul
    Zamani Saul is a South African politician who serves as the Premier of the Northern Cape province.
  • E. Dávid
    Dávid is a given name, commonly used in Hungarian and other languages as a form of the name David.
  • 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_69bd440c77948190aad2a5f39b7b80f5 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd86abc1e88190ad08279c3bf238e5 completed March 20, 2026, 5:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf3a96fba481909659b13425951068 completed March 22, 2026, 12:40 a.m.
Created at: March 20, 2026, 2:03 p.m.