Triple

T1861828
Position Surface form Disambiguated ID Type / Status
Subject Surah Al-Anbiya E34830 entity
Predicate containsStoryOf P6847 FINISHED
Object Prophet Dawud E142700 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: Prophet Dawud | Statement: [Surah Al-Anbiya, containsStoryOf, Prophet Dawud]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Prophet Dawud
Context triple: [Surah Al-Anbiya, containsStoryOf, Prophet Dawud]
  • A. Dawud chosen
    Dawud is a prophet and king in Islamic tradition, known for his wisdom, psalms, and just rule.
  • B. King David
    King David is the second king of ancient Israel, revered in Judaism as a foundational monarch, warrior, and psalmist whose dynasty is central to Jewish messianic tradition.
  • C. Dávid
    Dávid is a given name, commonly used in Hungarian and other languages as a form of the name David.
  • D. Shfar'am
    Shfar'am is an ancient, predominantly Arab city in northern Israel known for its historically mixed Muslim, Christian, and Druze population.
  • E. King Solomon
    King Solomon is a biblical king of ancient Israel renowned for his wisdom, wealth, and the construction of the First Temple in Jerusalem.
  • 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_69a88600b2f88190bc09303e68ab517e completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69abb09e714881909cef0f7e77b5b3b9 completed March 7, 2026, 4:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69add1d026748190a507872de85c908d completed March 8, 2026, 7:45 p.m.
Created at: March 4, 2026, 7:34 p.m.