Triple

T27489781
Position Surface form Disambiguated ID Type / Status
Subject 2000 Taiwanese presidential election E693845 entity
Predicate JamesSoongRunningMate P163268 FINISHED
Object Chang Chao-hsiung
Chang Chao-hsiung is a Taiwanese politician best known for serving as James Soong’s vice-presidential running mate in the 2000 Taiwanese presidential election.
E1783954 NE FINISHED

How this triple was built (3 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: Chang Chao-hsiung | Statement: [2000 Taiwanese presidential election, JamesSoongRunningMate, Chang Chao-hsiung]
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: Chang Chao-hsiung
Triple: [2000 Taiwanese presidential election, JamesSoongRunningMate, Chang Chao-hsiung]
Generated description
Chang Chao-hsiung is a Taiwanese politician best known for serving as James Soong’s vice-presidential running mate in the 2000 Taiwanese presidential election.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: JamesSoongRunningMate
Context triple: [2000 Taiwanese presidential election, JamesSoongRunningMate, Chang Chao-hsiung]
  • A. JamesSoongVotes
    Indicates that James Soong casts a vote or supports a particular candidate, policy, or decision.
  • B. JamesSoongVoteShare
    Indicates the proportion of total votes received by James Soong in a given election or electoral context.
  • C. دين رئيسي
    Indicates a primary or main religious affiliation that an entity predominantly follows or is associated with.
  • D. runningMateOfKrisKobach
    Indicates that one person served as Kris Kobach’s running mate on an electoral ticket.
  • E. runningMateOfAndrewGillum
    Indicates a person who was the vice-gubernatorial running mate on the same ticket as Andrew Gillum in an election.
  • F. None of above. chosen

Provenance (7 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_69ef5382b9648190be0b1ef2ad5d043c completed April 27, 2026, 12:16 p.m.
NER Named-entity recognition batch_69f6369a22688190a5674191c90a5d12 completed May 2, 2026, 5:38 p.m.
NED1 Entity disambiguation (via context triple) batch_6a12da74c3b88190909e394cb28767db completed May 24, 2026, 11:01 a.m.
NEDg Description generation batch_6a12db2833688190af921e97c6e5d05d completed May 24, 2026, 11:04 a.m.
NED2 Entity disambiguation (via description) batch_6a12db977df48190b71bce8408b51269 completed May 24, 2026, 11:05 a.m.
PD Predicate disambiguation batch_69f631871c888190bf29466fe4254e51 completed May 2, 2026, 5:16 p.m.
PDg Predicate description generation batch_69f6359d46b88190922dd7de508e3b0e completed May 2, 2026, 5:34 p.m.
Created at: April 27, 2026, 1:04 p.m.