Triple

T13436634
Position Surface form Disambiguated ID Type / Status
Subject Alnmouth railway station E320245 entity
Predicate hasStationCode P1289 FINISHED
Object ALM
ALM is the National Rail station code for Alnmouth railway station in Northumberland, England.
 E1041712 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: ALM | Statement: [Alnmouth railway station, hasStationCode, ALM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ALM
Context triple: [Alnmouth railway station, hasStationCode, ALM]
  • A. ALM (company)
    ALM (company) is a media and information services firm best known for publishing legal and business news, including leading industry rankings such as the Am Law 100.
  • B. ALCOM
    ALCOM is the abbreviated designation for Alaskan Command, a U.S. military command responsible for defense operations in and around Alaska.
  • C. ALC
    ALC is the IATA airport code for Alicante–Elche Airport, the main international airport serving Spain’s Costa Blanca region.
  • D. ALG
    ALG is the IATA airport code for Houari Boumediene Airport, the main international airport serving Algiers, Algeria.
  • E. ALP
    ALP is the commonly used abbreviation for the Australian Labor Party, a major centre-left political party in Australia.
  • 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: ALM
Triple: [Alnmouth railway station, hasStationCode, ALM]
Generated description
ALM is the National Rail station code for Alnmouth railway station in Northumberland, England.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ALM
Target entity description: ALM is the National Rail station code for Alnmouth railway station in Northumberland, England.
  • A. ALM (company)
    ALM (company) is a media and information services firm best known for publishing legal and business news, including leading industry rankings such as the Am Law 100.
  • B. ALCOM
    ALCOM is the abbreviated designation for Alaskan Command, a U.S. military command responsible for defense operations in and around Alaska.
  • C. ALC
    ALC is the IATA airport code for Alicante–Elche Airport, the main international airport serving Spain’s Costa Blanca region.
  • D. ALG
    ALG is the IATA airport code for Houari Boumediene Airport, the main international airport serving Algiers, Algeria.
  • E. ALP
    ALP is the commonly used abbreviation for the Australian Labor Party, a major centre-left political party in Australia.
  • 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_69d80761e6cc8190a90c844589998ecc completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbaee42a8c8190a85716b4a6db335e completed April 12, 2026, 2:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69f739902d148190ac14ac66f1f9512f completed May 3, 2026, 12:03 p.m.
NEDg Description generation batch_69f73d6051e48190a39e8de98bfb839a completed May 3, 2026, 12:19 p.m.
NED2 Entity disambiguation (via description) batch_69f7411fbb9481908f0106b01f2583bf completed May 3, 2026, 12:35 p.m.
Created at: April 9, 2026, 9:40 p.m.