Triple

T2260300
Position Surface form Disambiguated ID Type / Status
Subject Kaspi E50021 entity
Predicate regionCapital P16248 FINISHED
Object Gori E1743 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: Gori | Statement: [Kaspi, regionCapital, Gori]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gori
Context triple: [Kaspi, regionCapital, Gori]
  • A. Gori chosen
    Gori is a city in central Georgia best known as the birthplace of Soviet leader Joseph Stalin.
  • B. Ḍogrī
    Ḍogrī is the native name of the Dogri language, an Indo-Aryan language spoken primarily in the Jammu region of India.
  • C. Tyrnyauz
    Tyrnyauz is a mountainous town in southwestern Russia known for its former tungsten-molybdenum mining industry and location in the North Caucasus.
  • D. Shughni
    Shughni is an Eastern Iranian language spoken primarily in the Badakhshan region of Tajikistan and Afghanistan, known for its use among the Shughni people in the Pamir Mountains.
  • E. Ejersa Goro
    Ejersa Goro is a town in eastern Ethiopia notable as the birthplace of Emperor Haile Selassie I.
  • 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_69a88b01e0048190ba96431b5f990ba9 completed March 4, 2026, 7:41 p.m.
NER Named-entity recognition batch_69abc15be1288190a55c12674f4a5e03 completed March 7, 2026, 6:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae7f08f2b88190bba173acb132a160 completed March 9, 2026, 8:04 a.m.
Created at: March 4, 2026, 7:48 p.m.