Triple

T8342930
Position Surface form Disambiguated ID Type / Status
Subject State of Yan E195965 entity
Predicate capital P234 FINISHED
Object Ji
Ji was an ancient Chinese city that served as the political and cultural center of the State of Yan during the Zhou dynasty period.
 E728439 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: Ji | Statement: [State of Yan, capital, Ji]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ji
Context triple: [State of Yan, capital, Ji]
  • A. Jish
    Jish is a village in northern Israel, historically significant for its mixed Maronite Christian and Muslim population and its location near the Lebanese border.
  • B. Junshi
    Junshi was the courtesy name of Sima Guang, a prominent Song dynasty historian and statesman best known for compiling the comprehensive chronicle "Zizhi Tongjian."
  • C. Iri Ji
    Iri Ji is a traditional Igbo cultural celebration in Nigeria that marks the harvest and offering of new yams, featuring rituals, feasting, and communal festivities.
  • D. Yeji
    Yeji is a town in central Ghana situated on the shores of Lake Volta, known as a local fishing and trading hub.
  • E. Jiyun
    Jiyun is an 11th-century Chinese rime dictionary that systematically records and organizes the phonology and characters of Middle Chinese.
  • 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: Ji
Triple: [State of Yan, capital, Ji]
Generated description
Ji was an ancient Chinese city that served as the political and cultural center of the State of Yan during the Zhou dynasty period.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ji
Target entity description: Ji was an ancient Chinese city that served as the political and cultural center of the State of Yan during the Zhou dynasty period.
  • A. Jish
    Jish is a village in northern Israel, historically significant for its mixed Maronite Christian and Muslim population and its location near the Lebanese border.
  • B. Junshi
    Junshi was the courtesy name of Sima Guang, a prominent Song dynasty historian and statesman best known for compiling the comprehensive chronicle "Zizhi Tongjian."
  • C. Iri Ji
    Iri Ji is a traditional Igbo cultural celebration in Nigeria that marks the harvest and offering of new yams, featuring rituals, feasting, and communal festivities.
  • D. Yeji
    Yeji is a town in central Ghana situated on the shores of Lake Volta, known as a local fishing and trading hub.
  • E. Jiyun
    Jiyun is an 11th-century Chinese rime dictionary that systematically records and organizes the phonology and characters of Middle Chinese.
  • 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_69ca82ecbdc481908a55cad8ca062d88 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb7febde288190bf4677fb24d26b83 completed March 31, 2026, 8:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69cdc72bc43c81909d95c7eb6aefc403 completed April 2, 2026, 1:32 a.m.
NEDg Description generation batch_69cdcb90bec88190a2c19681405aa13e completed April 2, 2026, 1:51 a.m.
NED2 Entity disambiguation (via description) batch_69cdcd0fc9488190a0a576c385b9bc1f completed April 2, 2026, 1:57 a.m.
Created at: March 30, 2026, 5:58 p.m.