Triple

T16946092
Position Surface form Disambiguated ID Type / Status
Subject Battle of Hengyang E411072 entity
Predicate location P40 FINISHED
Object Hengyang E168458 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: Hengyang | Statement: [Battle of Hengyang, location, Hengyang]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hengyang
Context triple: [Battle of Hengyang, location, Hengyang]
  • A. Hengyang chosen
    Hengyang is a major industrial and transportation hub city in southern China, located along the Xiang River in the south of Hunan Province.
  • B. Huaihua
    Huaihua is a prefecture-level city in southwestern Hunan Province, China, known as a regional transportation hub and home to several ethnic minority communities.
  • C. Yongzhou
    Yongzhou is a prefecture-level city in southern Hunan Province, China, known for its long history and location at the confluence of the Xiang and Xiao rivers.
  • D. Changde
    Changde is a city in northwestern Hunan Province, China, historically significant as a major battleground during the Second Sino-Japanese War.
  • E. Chenzhou
    Chenzhou is a prefecture-level city in southern Hunan Province, China, known as a regional transport hub and for its rich mineral resources and scenic mountainous landscapes.
  • 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_69d886c886688190967be07322597ac9 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3cfb25e0c8190948e62d9575ae9cd completed April 18, 2026, 6:38 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00cfeca4208190a3b9270869063d3d completed May 10, 2026, 6:35 p.m.
Created at: April 10, 2026, 5:31 a.m.