Triple

T15585017
Position Surface form Disambiguated ID Type / Status
Subject Wahidi Sultanates E374595 entity
Predicate capital P234 FINISHED
Object Azzan E1085232 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: Azzan | Statement: [Wahidi Sultanates, capital, Azzan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Azzan
Context triple: [Wahidi Sultanates, capital, Azzan]
  • A. Azzan chosen
    Azzan is a town in Yemen that serves as the administrative center of the Wahidi area.
  • B. Fazza
    Fazza is the popular pen name of Sheikh Hamdan bin Mohammed Al Maktoum, the Crown Prince of Dubai and a well-known Emirati poet and public figure.
  • C. Al-Azza
    Al-Azza is a Palestinian refugee camp located near Bethlehem in the West Bank, known for its dense population and longstanding refugee community.
  • D. Azna
    Azna is a small city in western Iran known for its location in the mountainous Lorestan region and its role as a local administrative and commercial center.
  • E. Hamzaa
    Hamzaa is a British R&B and soul singer-songwriter known for her emotive vocals and introspective, heartfelt lyrics.
  • 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_69d85ccd575081908909b71a3f3e3a61 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e47971481909e986dd999354628 completed April 16, 2026, 2:49 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff4c4f71e48190a15eb0a2138f083f completed May 9, 2026, 3:01 p.m.
Created at: April 10, 2026, 4:11 a.m.