Triple

T4204859
Position Surface form Disambiguated ID Type / Status
Subject Genpei War E86158 entity
Predicate namedAfter P63 FINISHED
Object Heishi clan E273026 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: Heishi clan | Statement: [Genpei War, namedAfter, Heishi clan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Heishi clan
Context triple: [Genpei War, namedAfter, Heishi clan]
  • A. Javanshir clan
    The Javanshir clan was a prominent Azerbaijani noble family that played a significant political and military role in the Karabakh region.
  • B. Xiong clan
    The Xiong clan was the hereditary noble family that provided the kings of the ancient Chinese state of Chu during the Zhou dynasty.
  • C. Naya clan
    The Naya clan is an ancient Jain lineage traditionally associated with the family background of Mahavira, the 24th Tirthankara of Jainism.
  • D. Yamato clan chosen
    The Yamato clan was the dominant ruling family of early Japan that laid the foundations of the imperial line and centralized state during the formative centuries of Japanese history.
  • E. Snipe clan
    The Snipe clan is one of the traditional matrilineal clans of the Cayuga people, associated with the snipe bird and integral to their social and kinship structure.
  • 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_69aed93b89f48190a31f6d57c760e42f completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69af0382eafc8190946bf45bf28095dd completed March 9, 2026, 5:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69b58a19c90c819083a750fafa6fd1c7 completed March 14, 2026, 4:17 p.m.
Created at: March 9, 2026, 3:49 p.m.