Triple

T15644084
Position Surface form Disambiguated ID Type / Status
Subject Hakka Affairs Council E376134 entity
Predicate abbreviation P43 FINISHED
Object HAC
HAC is the acronym for Taiwan’s Hakka Affairs Council, a government body responsible for promoting and preserving Hakka culture and language.
E1167580 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: HAC | Statement: [Hakka Affairs Council, abbreviation, HAC]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: HAC
Context triple: [Hakka Affairs Council, abbreviation, HAC]
  • A. HCAC
    HCAC is an NCAA Division III athletic conference composed primarily of small colleges in the Midwestern United States.
  • B. Le HAC
    Le HAC is a French professional football club based in Le Havre, known as one of the oldest football clubs in France.
  • C. HAF
    HAF is the commonly used abbreviation for the Hellenic Air Force, the air warfare branch of Greece’s armed forces.
  • D. HAJ
    HAJ is the three-letter IATA airport code for Hannover Airport in Hanover, Germany.
  • E. HAA
    HAA is the Harvard Alumni Association, the organization that connects and serves Harvard University’s global community of alumni.
  • 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: HAC
Triple: [Hakka Affairs Council, abbreviation, HAC]
Generated description
HAC is the acronym for Taiwan’s Hakka Affairs Council, a government body responsible for promoting and preserving Hakka culture and language.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: HAC
Target entity description: HAC is the acronym for Taiwan’s Hakka Affairs Council, a government body responsible for promoting and preserving Hakka culture and language.
  • A. HCAC
    HCAC is an NCAA Division III athletic conference composed primarily of small colleges in the Midwestern United States.
  • B. Le HAC
    Le HAC is a French professional football club based in Le Havre, known as one of the oldest football clubs in France.
  • C. HAF
    HAF is the commonly used abbreviation for the Hellenic Air Force, the air warfare branch of Greece’s armed forces.
  • D. HAJ
    HAJ is the three-letter IATA airport code for Hannover Airport in Hanover, Germany.
  • E. HAA
    HAA is the Harvard Alumni Association, the organization that connects and serves Harvard University’s global community of alumni.
  • 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_69d85cd035a48190b73d5579ab73969a completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04ed400ec8190a14a9f7cf3092865 completed April 16, 2026, 2:52 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff5f4e558481909a39fdc5d104994a completed May 9, 2026, 4:22 p.m.
NEDg Description generation batch_69ff5ffaefb4819094468ff0008740f8 completed May 9, 2026, 4:25 p.m.
NED2 Entity disambiguation (via description) batch_69ff6062f0ac819081270f270ce2f057 completed May 9, 2026, 4:27 p.m.
Created at: April 10, 2026, 4:15 a.m.