Triple

T9064918
Position Surface form Disambiguated ID Type / Status
Subject Zaza people E217221 entity
Predicate ethnonym P4709 FINISHED
Object Dimilis E776553 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: Dimilis | Statement: [Zaza people, ethnonym, Dimilis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dimilis
Context triple: [Zaza people, ethnonym, Dimilis]
  • A. Dilios
    Dilios is the Spartan soldier and narrator in the film "300," known for recounting King Leonidas's stand at Thermopylae.
  • B. Dimili chosen
    Dimili is an alternative ethnonym historically used to refer to the Zaza people, an ethnic group primarily inhabiting eastern Anatolia in modern-day Turkey.
  • C. Domokos
    Domokos is a town in central Greece known for its strategic hilltop location overlooking the Thessalian plain and its role as a local administrative and transport hub.
  • D. Damaskinos
    Damaskinos is a Greek-origin surname historically associated with notable religious and cultural figures.
  • E. Deliamber
    Deliamber is a powerful and enigmatic sorcerer from Robert Silverberg’s Majipoor series, serving as one of the key magical advisors and allies to Lord Valentine.
  • 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_69ca83d5a7f48190b16c1e59bd43ede0 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cc94bb26588190b7d6f2d70819e86f completed April 1, 2026, 3:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69d017a3926881909140f59c60ec3588 completed April 3, 2026, 7:40 p.m.
Created at: March 30, 2026, 7:11 p.m.