Triple

T15661392
Position Surface form Disambiguated ID Type / Status
Subject RCTP E376573 entity
Predicate ICAOcode P419 FINISHED
Object RCTP E376573 NE FINISHED

How this triple was built (2 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: RCTP | Statement: [RCTP, ICAOcode, RCTP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: RCTP
Context triple: [RCTP, ICAOcode, RCTP]
  • A. RCTP chosen
    RCTP is the ICAO airport code for Taiwan Taoyuan International Airport, the main international gateway serving Taipei and northern Taiwan.
  • B. RCTC
    RCTC is a regional agency responsible for planning, funding, and coordinating transportation projects and services in Riverside County, California.
  • C. RPTA
    RPTA is a regional public transportation authority responsible for planning, operating, and coordinating transit services within a specific geographic area.
  • D. RTRA
    RTRA is the abbreviation for the Royal Tank Regiment Association, an organization that supports and connects current and former members of the Royal Tank Regiment.
  • E. RTA
    RTA is Dubai’s Roads and Transport Authority, the government agency responsible for planning and operating the emirate’s public transportation and road systems.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d85cd1564c8190991adda63bfab4b0 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04ef4e6a08190ad8bbafaa3612f22 completed April 16, 2026, 2:52 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff679e0f2c8190bbcb7051c38e1580 completed May 9, 2026, 4:58 p.m.
Created at: April 10, 2026, 4:15 a.m.