Triple

T3637957
Position Surface form Disambiguated ID Type / Status
Subject Taipei Metro E77116 entity
Predicate abbreviation P43 FINISHED
Object TRTS
TRTS is the commonly used abbreviation for the Taipei Metro rapid transit system serving the Taipei metropolitan area in Taiwan.
 E376160 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: TRTS | Statement: [Taipei Metro, abbreviation, TRTS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: TRTS
Context triple: [Taipei Metro, abbreviation, TRTS]
  • A. TRST
    TRST is an optional active-low reset signal used in JTAG (IEEE 1149.1) interfaces to asynchronously reset the test access port controller.
  • B. TRT
    TRT is the time zone used in Turkey, corresponding to UTC+3.
  • C. TRT
    TRT is Turkey's national public broadcaster, operating multiple television and radio channels domestically and internationally.
  • D. TR
    TR is the two-letter ISO 3166-1 alpha-2 country code assigned to Turkey for international standardization and referencing.
  • E. RTR
    RTR is the commonly used nickname for the Recruit Training Regiment, a military unit responsible for initial training of new recruits.
  • 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: TRTS
Triple: [Taipei Metro, abbreviation, TRTS]
Generated description
TRTS is the commonly used abbreviation for the Taipei Metro rapid transit system serving the Taipei metropolitan area in Taiwan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: TRTS
Target entity description: TRTS is the commonly used abbreviation for the Taipei Metro rapid transit system serving the Taipei metropolitan area in Taiwan.
  • A. TRST
    TRST is an optional active-low reset signal used in JTAG (IEEE 1149.1) interfaces to asynchronously reset the test access port controller.
  • B. TRT
    TRT is the time zone used in Turkey, corresponding to UTC+3.
  • C. TRT
    TRT is Turkey's national public broadcaster, operating multiple television and radio channels domestically and internationally.
  • D. TR
    TR is the two-letter ISO 3166-1 alpha-2 country code assigned to Turkey for international standardization and referencing.
  • E. RTR
    RTR is the commonly used nickname for the Recruit Training Regiment, a military unit responsible for initial training of new recruits.
  • 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_69ad85dd0be48190b738990cb20c4731 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc328e5e481909d26318c743bc84a completed March 8, 2026, 6:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69b44f23298481909d313d6b3f8013cd completed March 13, 2026, 5:53 p.m.
NEDg Description generation batch_69b450785378819090b4ed7536db7757 completed March 13, 2026, 5:59 p.m.
NED2 Entity disambiguation (via description) batch_69b45a0afef8819097c6e87127b4d1db completed March 13, 2026, 6:40 p.m.
Created at: March 8, 2026, 3:24 p.m.