Triple

T14522225
Position Surface form Disambiguated ID Type / Status
Subject Abdi Farah Shirdon E340679 entity
Predicate spouse P13 FINISHED
Object Asha Haji Elmi E19490 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: Asha Haji Elmi | Statement: [Abdi Farah Shirdon, spouse, Asha Haji Elmi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Asha Haji Elmi
Context triple: [Abdi Farah Shirdon, spouse, Asha Haji Elmi]
  • A. Hadya Sher Ali
    Hadya Sher Ali is a Pakistani woman known primarily for her brief marriage to British-Pakistani heart surgeon Hasnat Khan.
  • B. Fatima Namazi
    Fatima Namazi is a member of the Office of Special Projects, contributing to its specialized initiatives and operations.
  • C. Hawa Abdi
    Hawa Abdi was a pioneering Somali doctor, human rights activist, and humanitarian who founded a hospital and refuge for tens of thousands of displaced people during her country’s civil war.
  • D. Asha Hagi Elmi chosen
    Asha Hagi Elmi is a Somali peace activist and politician renowned for her work in promoting women's participation in peace processes and rebuilding civil society in Somalia.
  • E. Safa Zaki
    Safa Zaki is a cognitive psychologist and academic leader who became the first woman to serve as president of Bowdoin College.
  • 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_69d822dac79c8190a84a073f3cbaced5 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69de9a72cff08190878b4bed9b0b5eb5 completed April 14, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd8ab07e08819085a6a21cc9cea1fa completed May 8, 2026, 7:03 a.m.
Created at: April 10, 2026, 1:22 a.m.