Triple

T7877598
Position Surface form Disambiguated ID Type / Status
Subject Rula Ghani E182895 entity
Predicate spouse P13 FINISHED
Object Ashraf Ghani E34442 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: Ashraf Ghani | Statement: [Rula Ghani, spouse, Ashraf Ghani]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ashraf Ghani
Context triple: [Rula Ghani, spouse, Ashraf Ghani]
  • A. Ashraf Ghani chosen
    Ashraf Ghani is an Afghan academic and politician who served as President of Afghanistan from 2014 until the Taliban takeover in 2021.
  • B. Hibatullah Akhundzada
    Hibatullah Akhundzada is the supreme leader of the Taliban and the de facto top authority in Afghanistan since the group’s return to power in 2021.
  • C. Abdullah Abdullah
    Abdullah Abdullah is an Afghan politician and former foreign minister who became a prominent opposition leader and key figure in post-Taliban Afghan politics.
  • D. Mousa Ghani
    Mousa Ghani is a supporting character in the action film "Rambo III," serving as an Afghan guide and ally to John Rambo during his mission.
  • E. Hamid Karzai
    Hamid Karzai is an Afghan politician who served as the country’s first post-Taliban president, leading Afghanistan through the early years of the U.S.-led intervention and subsequent reconstruction efforts.
  • 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_69ca828a17248190b46defe758bc5ad3 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb39bc07208190aa452cef8ca5b0d6 completed March 31, 2026, 3:04 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd9423b4608190acbe4a3141890a05 completed April 1, 2026, 9:54 p.m.
Created at: March 30, 2026, 4:57 p.m.