Triple

T10157076
Position Surface form Disambiguated ID Type / Status
Subject Ma'in E233800 entity
Predicate archaeologicalSite P1098 FINISHED
Object Qarnāwu E657270 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: Qarnāwu | Statement: [Ma'in, archaeologicalSite, Qarnāwu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Qarnāwu
Context triple: [Ma'in, archaeologicalSite, Qarnāwu]
  • A. Qarnāwu chosen
    Qarnāwu was an ancient South Arabian city that served as the political and economic center of the Minaean kingdom in what is now Yemen.
  • B. Qafar
    Qafar is another name for the Afar people, a Cushitic ethnic group primarily inhabiting the Horn of Africa, especially in Ethiopia, Eritrea, and Djibouti.
  • C. Qarin
    A Qarin is a Muslim pilgrim who performs Hajj and ‘Umrah together in a single journey without exiting the state of ihram between them.
  • D. Qurbono
    Qurbono is the term used in Syriac Christianity for the Divine Liturgy, the central Eucharistic worship service.
  • E. Al Qara
    Al Qara is a town in southwestern Saudi Arabia located within the mountainous Al Bahah Region.
  • 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_69ca848e80748190b91d1e04d35512c7 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cdec3c47dc81909679903e6024eb49 completed April 2, 2026, 4:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69d3176ac9388190bc76b3cffce93a3d completed April 6, 2026, 2:16 a.m.
Created at: March 30, 2026, 9:09 p.m.