Triple

T9121053
Position Surface form Disambiguated ID Type / Status
Subject Royal Corps of Transport E218848 entity
Predicate hasAbbreviation P43 FINISHED
Object RCT E218848 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: RCT | Statement: [Royal Corps of Transport, hasAbbreviation, RCT]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: RCT
Context triple: [Royal Corps of Transport, hasAbbreviation, RCT]
  • A. RCT chosen
    RCT is the abbreviation for the Royal Corps of Transport, a former corps of the British Army responsible for military transport and logistics.
  • B. RCTC
    RCTC is a regional agency responsible for planning, funding, and coordinating transportation projects and services in Riverside County, California.
  • C. RCTP
    RCTP is the ICAO airport code for Taiwan Taoyuan International Airport, the main international gateway serving Taipei and northern Taiwan.
  • D. INA trials
    INA trials were a series of high-profile court-martials held by the British colonial government in 1945–46 to prosecute officers and soldiers of Subhas Chandra Bose’s Indian National Army, which became a major catalyst for India’s independence movement.
  • E. ResearchKit
    ResearchKit is an open-source framework from Apple that enables researchers and developers to create iOS apps for conducting medical studies and collecting health-related data from participants.
  • 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_69ca83dddd548190983b96c664f7f367 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cca8b32ba88190b2b4406c7b905cca completed April 1, 2026, 5:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69d047c55a988190bf2dd63a0d0a2743 completed April 3, 2026, 11:05 p.m.
Created at: March 30, 2026, 7:17 p.m.