Triple

T3072428
Position Surface form Disambiguated ID Type / Status
Subject Shushan Purim E64054 entity
Predicate namedAfter P63 FINISHED
Object Shushan E325270 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: Shushan | Statement: [Shushan Purim, namedAfter, Shushan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shushan
Context triple: [Shushan Purim, namedAfter, Shushan]
  • A. Shushan chosen
    Shushan is the ancient Persian royal city traditionally identified as the capital where the events of the biblical Book of Esther take place.
  • B. Mount Ebal
    Mount Ebal is a prominent mountain in the West Bank historically significant in biblical tradition, particularly as the site associated with the curses in the covenant ceremony described in the Book of Deuteronomy.
  • C. Eglah
    Eglah is a lesser-known wife of the biblical King David, mentioned among the mothers of his sons in the Hebrew Bible.
  • D. Gilboa Mountains
    The Gilboa Mountains are a mountain range in northern Israel known for their scenic landscapes, biblical associations, and views over the Jezreel Valley.
  • E. Safed Koh
    Safed Koh is a prominent mountain range along the Afghanistan–Pakistan border, known for its high, rugged peaks and strategic passes near the Khyber region.
  • 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_69ad857a8aec8190bfdfd9c14554ac5a completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada14c8bd881909cf1bb2649ba36db completed March 8, 2026, 4:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69b20f49ed80819087226b3eaf81965b completed March 12, 2026, 12:56 a.m.
Created at: March 8, 2026, 3:02 p.m.