Triple

T17901857
Position Surface form Disambiguated ID Type / Status
Subject Battle of Lichuan E447598 entity
Predicate location P40 FINISHED
Object Lichuan
Lichuan is a city in southwestern Hubei Province, China, historically noted as the site of the Battle of Lichuan.
 E1296071 NE FINISHED

How this triple was built (4 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: Lichuan | Statement: [Battle of Lichuan, location, Lichuan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lichuan
Context triple: [Battle of Lichuan, location, Lichuan]
  • A. Luzhou
    Luzhou is a prefecture-level city in southern Sichuan, China, known for its historic river port and famous strong-aroma baijiu liquor industry.
  • B. Luzhou
    Luzhou is an old historical name for the city now known as Hefei, the capital of Anhui Province in eastern China.
  • C. Xichang
    Xichang is a city in Sichuan Province, China, known as a major hub for the country’s space launch activities and related aerospace industry.
  • D. Yibin
    Yibin is a historic prefecture-level city in southwestern China known as the "First City on the Yangtze River," where the Jinsha and Min rivers converge to form the Yangtze.
  • E. Quidong
    Quidong is a rural locality in New South Wales, Australia, situated within the Snowy Monaro region.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Lichuan
Triple: [Battle of Lichuan, location, Lichuan]
Generated description
Lichuan is a city in southwestern Hubei Province, China, historically noted as the site of the Battle of Lichuan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lichuan
Target entity description: Lichuan is a city in southwestern Hubei Province, China, historically noted as the site of the Battle of Lichuan.
  • A. Luzhou
    Luzhou is a prefecture-level city in southern Sichuan, China, known for its historic river port and famous strong-aroma baijiu liquor industry.
  • B. Luzhou
    Luzhou is an old historical name for the city now known as Hefei, the capital of Anhui Province in eastern China.
  • C. Xichang
    Xichang is a city in Sichuan Province, China, known as a major hub for the country’s space launch activities and related aerospace industry.
  • D. Yibin
    Yibin is a historic prefecture-level city in southwestern China known as the "First City on the Yangtze River," where the Jinsha and Min rivers converge to form the Yangtze.
  • E. Quidong
    Quidong is a rural locality in New South Wales, Australia, situated within the Snowy Monaro region.
  • F. None of above. chosen

Provenance (5 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_69d8b9f59bd48190a6fc925a855b8bac completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49e98fb688190815ac308e5ed7fde completed April 19, 2026, 9:21 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0321271ebc8190ba244c524c57a6b3 completed May 12, 2026, 12:46 p.m.
NEDg Description generation batch_6a0321d2a9cc8190aafcc7305f488dac completed May 12, 2026, 12:49 p.m.
NED2 Entity disambiguation (via description) batch_6a0322425c248190a95042ebfcb98589 completed May 12, 2026, 12:51 p.m.
Created at: April 10, 2026, 10:19 a.m.