Triple

T20406269
Position Surface form Disambiguated ID Type / Status
Subject Akbar Hashemi Rafsanjani E500475 entity
Predicate familyName P18 FINISHED
Object Hashemi 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: Hashemi | Statement: [Akbar Hashemi Rafsanjani, familyName, Hashemi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hashemi
Context triple: [Akbar Hashemi Rafsanjani, familyName, Hashemi]
  • A. Al-Hashemi chosen
    Al-Hashemi is a prominent Arabic dynastic family name historically associated with the descendants of the Prophet Muhammad and ruling houses in the Middle East.
  • B. Hesam
    Hesam is the birth name of Sam Asghari, the Iranian-American model, actor, and fitness trainer known for his marriage to Britney Spears.
  • C. Nasiri
    Nasiri is the family name of the ruling house of the Nasiri dynasty, a historical Muslim dynasty.
  • D. Hamid
    Hamid is a common Arabic-origin surname used by various notable individuals across the Muslim world and diaspora.
  • E. Ebrahimi
    Ebrahimi is a Persian-origin surname commonly found in Iran and among the global Iranian diaspora.
  • 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_69e0b4a81bec8190b69adfdc1336a015 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e67992cfb88190ae49a1723e6667a1 completed April 20, 2026, 7:08 p.m.
Created at: April 16, 2026, 11:29 a.m.