Triple

T15876070
Position Surface form Disambiguated ID Type / Status
Subject Khosrow and Shirin E384955 entity
Predicate relatedWork P37 FINISHED
Object Eskandar-nama E625404 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: Eskandar-nama | Statement: [Khosrow and Shirin, relatedWork, Eskandar-nama]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Eskandar-nama
Context triple: [Khosrow and Shirin, relatedWork, Eskandar-nama]
  • A. Eskandar-nameh chosen
    Eskandar-nameh is a medieval Persian epic poem by Nizami Ganjavi that recounts the legendary adventures and philosophical journeys of Alexander the Great.
  • B. Eskandar
    Eskandar is a Persian and Arabic form of the name Alexander, commonly used in historical and literary contexts to refer to Alexander the Great.
  • C. Eskandarian
    Eskandarian is a surname most notably associated with Alecko Eskandarian, a former professional American soccer player and coach.
  • D. King Shahdov
    King Shahdov is the exiled monarch and central figure of Charlie Chaplin’s satirical film "A King in New York," through whom the movie critiques American politics, media, and McCarthy-era paranoia.
  • E. Alaeddin
    Alaeddin was an early Ottoman statesman and son of Osman I, often regarded as the first Ottoman grand vizier.
  • 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_69d86da4e86481909f1325fdc971b5ec completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e155fdc1b881909d1c82c4c66a195a completed April 16, 2026, 9:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffa94e9b548190bec74e6d9790d241 completed May 9, 2026, 9:38 p.m.
Created at: April 10, 2026, 4:51 a.m.