Triple

T23205253
Position Surface form Disambiguated ID Type / Status
Subject Hounslow East Underground station E580434 entity
Predicate stationCode P1289 FINISHED
Object HWE
HWE is the three-letter station code used to identify Hounslow East Underground station on the London Underground network.
 E1575894 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: HWE | Statement: [Hounslow East Underground station, stationCode, HWE]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: HWE
Context triple: [Hounslow East Underground station, stationCode, HWE]
  • A. H.W
    H.W is the workshop mark used by Henrik Wigström, a prominent Finnish-born Fabergé workmaster known for crafting exquisite jeweled objects and imperial Easter eggs.
  • B. HEL
    HEL is the three-letter IATA airport code for Helsinki Airport, the main international gateway to Finland’s capital region.
  • C. WHE
    WHE is the National Rail station code for Whalley railway station in Lancashire, England.
  • D. HE
    HE is the Faculty of Health at Aarhus University, responsible for education and research in medical and health sciences.
  • E. HWA
    HWA is the commonly used acronym for the Horror Writers Association, an international organization dedicated to promoting and supporting creators of horror and dark fiction.
  • 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: HWE
Triple: [Hounslow East Underground station, stationCode, HWE]
Generated description
HWE is the three-letter station code used to identify Hounslow East Underground station on the London Underground network.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: HWE
Target entity description: HWE is the three-letter station code used to identify Hounslow East Underground station on the London Underground network.
  • A. H.W
    H.W is the workshop mark used by Henrik Wigström, a prominent Finnish-born Fabergé workmaster known for crafting exquisite jeweled objects and imperial Easter eggs.
  • B. HEL
    HEL is the three-letter IATA airport code for Helsinki Airport, the main international gateway to Finland’s capital region.
  • C. WHE
    WHE is the National Rail station code for Whalley railway station in Lancashire, England.
  • D. HE
    HE is the Faculty of Health at Aarhus University, responsible for education and research in medical and health sciences.
  • E. HWA
    HWA is the commonly used acronym for the Horror Writers Association, an international organization dedicated to promoting and supporting creators of horror and dark fiction.
  • 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_69e24602ae1481908aaa6bc7ca493867 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f1907c1d7c8190aca252a39ae0da86 completed April 29, 2026, 5 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c30c2ac508190ab718e22afde7a73 completed May 19, 2026, 9:43 a.m.
NEDg Description generation batch_6a0c332f5ef08190ab7f6536eb719e04 completed May 19, 2026, 9:53 a.m.
NED2 Entity disambiguation (via description) batch_6a0c374ded1c8190b1d5c7a3ab521cf9 completed May 19, 2026, 10:11 a.m.
Created at: April 17, 2026, 4:07 p.m.