Triple

T8006142
Position Surface form Disambiguated ID Type / Status
Subject Cornbrook tram stop E186367 entity
Predicate hasStationCode P1289 FINISHED
Object CRB
CRB is the station code for Cornbrook tram stop on the Manchester Metrolink light rail network in England.
 E701745 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: CRB | Statement: [Cornbrook tram stop, hasStationCode, CRB]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: CRB
Context triple: [Cornbrook tram stop, hasStationCode, CRB]
  • A. CRD
    CRD is a centralized online database maintained by FINRA that contains licensing and registration information on broker-dealers and their associated individuals in the U.S. financial industry.
  • B. CRD
    CRD is the IATA airport code for General Enrique Mosconi International Airport serving Comodoro Rivadavia in Argentina.
  • C. CRK
    CRK is the IATA airport code for Clark International Airport, a major aviation hub located in Pampanga, Philippines.
  • D. CRUI
    CRUI is the Conference of Italian University Rectors, a national association representing and coordinating the leadership of Italian universities.
  • E. CBNB
    CBNB is a specialized chemical database, likely focused on chemical substances and related data, accessible through the Engineering Village research platform.
  • 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: CRB
Triple: [Cornbrook tram stop, hasStationCode, CRB]
Generated description
CRB is the station code for Cornbrook tram stop on the Manchester Metrolink light rail network in England.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: CRB
Target entity description: CRB is the station code for Cornbrook tram stop on the Manchester Metrolink light rail network in England.
  • A. CRD
    CRD is a centralized online database maintained by FINRA that contains licensing and registration information on broker-dealers and their associated individuals in the U.S. financial industry.
  • B. CRD
    CRD is the IATA airport code for General Enrique Mosconi International Airport serving Comodoro Rivadavia in Argentina.
  • C. CRK
    CRK is the IATA airport code for Clark International Airport, a major aviation hub located in Pampanga, Philippines.
  • D. CRUI
    CRUI is the Conference of Italian University Rectors, a national association representing and coordinating the leadership of Italian universities.
  • E. CBNB
    CBNB is a specialized chemical database, likely focused on chemical substances and related data, accessible through the Engineering Village research platform.
  • 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_69ca82aaaf24819084b94d18f699ba53 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3cf72fc08190aa78b97c1ab92f90 completed March 31, 2026, 3:18 a.m.
NED1 Entity disambiguation (via context triple) batch_69cbe12c068c8190a6ea7e924a7748c6 completed March 31, 2026, 2:58 p.m.
NEDg Description generation batch_69cbe442999881909544802bb9a91cd5 completed March 31, 2026, 3:12 p.m.
NED2 Entity disambiguation (via description) batch_69cc09c676148190964d4947310ec16a completed March 31, 2026, 5:52 p.m.
Created at: March 30, 2026, 5:18 p.m.