Triple

T1453424
Position Surface form Disambiguated ID Type / Status
Subject London St Pancras International E31343 entity
Predicate railCode P18202 FINISHED
Object STP
STP is the three-letter National Rail station code for London St Pancras International railway station.
 E94967 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: STP | Statement: [London St Pancras International, railCode, STP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: STP
Context triple: [London St Pancras International, railCode, STP]
  • A. STP
    STP is the three-letter ISO 3166-1 alpha-3 country code for São Tomé and Príncipe, an island nation in the Gulf of Guinea off Central Africa.
  • B. STP-2
    STP-2 was a U.S. Department of Defense Space Test Program mission that used a SpaceX Falcon Heavy rocket to deploy multiple experimental and technology demonstration payloads into orbit.
  • C. STBP
    STBP is the acronym for the Stop TB Partnership, a global coalition dedicated to ending tuberculosis as a public health problem.
  • D. STN
    STN is the three-letter IATA airport code for London Stansted Airport, a major international airport serving the London area in the United Kingdom.
  • E. ST
    ST is the commonly used abbreviation for SkyTeam, a major global airline alliance.
  • 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: STP
Triple: [London St Pancras International, railCode, STP]
Generated description
STP is the three-letter National Rail station code for London St Pancras International railway station.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: STP
Target entity description: STP is the three-letter National Rail station code for London St Pancras International railway station.
  • A. STP chosen
    STP is the three-letter ISO 3166-1 alpha-3 country code for São Tomé and Príncipe, an island nation in the Gulf of Guinea off Central Africa.
  • B. STP-2
    STP-2 was a U.S. Department of Defense Space Test Program mission that used a SpaceX Falcon Heavy rocket to deploy multiple experimental and technology demonstration payloads into orbit.
  • C. STBP
    STBP is the acronym for the Stop TB Partnership, a global coalition dedicated to ending tuberculosis as a public health problem.
  • D. STN
    STN is the three-letter IATA airport code for London Stansted Airport, a major international airport serving the London area in the United Kingdom.
  • E. ST
    ST is the commonly used abbreviation for SkyTeam, a major global airline alliance.
  • F. None of above.

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_69a499171a28819085b993a3ac78e363 completed March 1, 2026, 7:52 p.m.
NER Named-entity recognition batch_69a4c57e82d48190a30a4512f39f5de0 completed March 1, 2026, 11:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad08c7db088190877addd5edd6c087 completed March 8, 2026, 5:27 a.m.
NEDg Description generation batch_69ad09ae79588190a64a0897352bfc28 completed March 8, 2026, 5:31 a.m.
NED2 Entity disambiguation (via description) batch_69ad0ac635008190bb82bbb2c27adda5 completed March 8, 2026, 5:36 a.m.
Created at: March 1, 2026, 8 p.m.