Triple

T22826567
Position Surface form Disambiguated ID Type / Status
Subject Haltwhistle railway station E565675 entity
Predicate stationCode P1289 FINISHED
Object HWH
HWH is the National Rail station code for Haltwhistle railway station in Northumberland, England.
E727488 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: HWH | Statement: [Haltwhistle railway station, stationCode, HWH]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: HWH
Context triple: [Haltwhistle railway station, stationCode, HWH]
  • A. HWH
    HWH is the station code for Howrah Junction, one of India’s busiest and oldest major railway terminals serving the Kolkata metropolitan area.
  • B. HWD
    HWD is the three-letter IATA airport code assigned to Hayward Executive Airport in Hayward, California.
  • C. WHE
    WHE is the National Rail station code for Whalley railway station in Lancashire, England.
  • D. WRH
    WRH is the National Rail station code for Worthing railway station in West Sussex, England.
  • E. MWH
    MWH is the IATA airport code for Grant County International Airport, a large airfield in Moses Lake, Washington, used for commercial, military, and flight-testing operations.
  • 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: HWH
Triple: [Haltwhistle railway station, stationCode, HWH]
Generated description
HWH is the National Rail station code for Haltwhistle railway station in Northumberland, England.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: HWH
Target entity description: HWH is the National Rail station code for Haltwhistle railway station in Northumberland, England.
  • A. HWH chosen
    HWH is the station code for Howrah Junction, one of India’s busiest and oldest major railway terminals serving the Kolkata metropolitan area.
  • B. HWD
    HWD is the three-letter IATA airport code assigned to Hayward Executive Airport in Hayward, California.
  • C. WHE
    WHE is the National Rail station code for Whalley railway station in Lancashire, England.
  • D. WRH
    WRH is the National Rail station code for Worthing railway station in West Sussex, England.
  • E. MWH
    MWH is the IATA airport code for Grant County International Airport, a large airfield in Moses Lake, Washington, used for commercial, military, and flight-testing operations.
  • 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_69e24585ab1c81909b2b5065d15805d5 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17e2832b8819091c1dfd2cd598b90 completed April 29, 2026, 3:42 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0ba7a9fe148190906e142762462634 completed May 18, 2026, 11:58 p.m.
NEDg Description generation batch_6a0ba84676f8819099e4ad46797387d9 completed May 19, 2026, 12:01 a.m.
NED2 Entity disambiguation (via description) batch_6a0ba8fa53a88190a0029d884308ffd6 completed May 19, 2026, 12:04 a.m.
Created at: April 17, 2026, 3:34 p.m.