Triple

T18130674
Position Surface form Disambiguated ID Type / Status
Subject Haverfordwest railway station E434000 entity
Predicate hasStationCode P1289 FINISHED
Object HVF
HVF is the National Rail station code for Haverfordwest railway station in Pembrokeshire, Wales.
E1308540 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: HVF | Statement: [Haverfordwest railway station, hasStationCode, HVF]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: HVF
Context triple: [Haverfordwest railway station, hasStationCode, HVF]
  • A. HVF
    HVF is a data-focused startup and innovation lab created by entrepreneur Max Levchin to explore and build companies around large-scale data problems.
  • B. HVN
    HVN is the ICAO airline designator used to identify Vietnam Airlines in international aviation operations.
  • C. HVN
    HVN is the IATA airport code for Tweed New Haven Airport, a regional airport serving New Haven, Connecticut.
  • D. HVL
    HVL is the vehicle registration code used for motor vehicles registered in the Havelland district of Brandenburg, Germany.
  • E. VfGH
    VfGH is the abbreviation for Austria’s Constitutional Court, the highest judicial body responsible for reviewing the constitutionality of laws and safeguarding the Austrian constitution.
  • 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: HVF
Triple: [Haverfordwest railway station, hasStationCode, HVF]
Generated description
HVF is the National Rail station code for Haverfordwest railway station in Pembrokeshire, Wales.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: HVF
Target entity description: HVF is the National Rail station code for Haverfordwest railway station in Pembrokeshire, Wales.
  • A. HVF
    HVF is a data-focused startup and innovation lab created by entrepreneur Max Levchin to explore and build companies around large-scale data problems.
  • B. HVN
    HVN is the ICAO airline designator used to identify Vietnam Airlines in international aviation operations.
  • C. HVN
    HVN is the IATA airport code for Tweed New Haven Airport, a regional airport serving New Haven, Connecticut.
  • D. HVL
    HVL is the vehicle registration code used for motor vehicles registered in the Havelland district of Brandenburg, Germany.
  • E. VfGH
    VfGH is the abbreviation for Austria’s Constitutional Court, the highest judicial body responsible for reviewing the constitutionality of laws and safeguarding the Austrian constitution.
  • 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_69d8b909e8cc81908df4cc2b8ea6d11f completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4ddf1e2508190993f65ca137fdf63 completed April 19, 2026, 1:51 p.m.
NED1 Entity disambiguation (via context triple) batch_6a03854626e881908d46685bde4ad344 completed May 12, 2026, 7:53 p.m.
NEDg Description generation batch_6a0389649bac8190bb5f189e562ab8c3 completed May 12, 2026, 8:11 p.m.
NED2 Entity disambiguation (via description) batch_6a0389eb3928819080b6d257698e662c completed May 12, 2026, 8:13 p.m.
Created at: April 10, 2026, 10:29 a.m.