Triple

T17714126
Position Surface form Disambiguated ID Type / Status
Subject Witham railway station E442145 entity
Predicate hasStationCode P1289 FINISHED
Object WTM
WTM is the National Rail station code for Witham railway station in Essex, England.
E627989 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: WTM | Statement: [Witham railway station, hasStationCode, WTM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: WTM
Context triple: [Witham railway station, hasStationCode, WTM]
  • A. WTM
    WTM is the vehicle registration code used on license plates for vehicles registered in the Wittmund district of Lower Saxony, Germany.
  • B. WTW
    WTW is the abbreviation for "Walking Together on the Way," an ecumenical document focused on fostering unity and dialogue among Christian traditions.
  • C. WTN
    WTN is the IATA airport code for RAF Waddington, a Royal Air Force station in Lincolnshire, England.
  • D. WATH
    WATH is a local radio station serving the Athens, Ohio area with news, talk, and music programming.
  • E. WTK
    WTK is an alternative abbreviation commonly used to refer to the World Trade Center.
  • 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: WTM
Triple: [Witham railway station, hasStationCode, WTM]
Generated description
WTM is the National Rail station code for Witham railway station in Essex, England.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: WTM
Target entity description: WTM is the National Rail station code for Witham railway station in Essex, England.
  • A. WTM chosen
    WTM is the vehicle registration code used on license plates for vehicles registered in the Wittmund district of Lower Saxony, Germany.
  • B. WTW
    WTW is the abbreviation for "Walking Together on the Way," an ecumenical document focused on fostering unity and dialogue among Christian traditions.
  • C. WTN
    WTN is the IATA airport code for RAF Waddington, a Royal Air Force station in Lincolnshire, England.
  • D. WATH
    WATH is a local radio station serving the Athens, Ohio area with news, talk, and music programming.
  • E. WTK
    WTK is an alternative abbreviation commonly used to refer to the World Trade Center.
  • 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_69d8b9ec79688190b86bdcef85a7b3aa completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4729cebd08190872be96a26d0f7ce completed April 19, 2026, 6:13 a.m.
NED1 Entity disambiguation (via context triple) batch_6a023027e52c81908e320ae9a84b8874 completed May 11, 2026, 7:38 p.m.
NEDg Description generation batch_6a0230ae9f948190981751c9ca0e9031 completed May 11, 2026, 7:40 p.m.
NED2 Entity disambiguation (via description) batch_6a0234879d348190b023d0522318399d completed May 11, 2026, 7:56 p.m.
Created at: April 10, 2026, 10:06 a.m.