Triple

T6708104
Position Surface form Disambiguated ID Type / Status
Subject Fareham railway station E153058 entity
Predicate stationCode P1289 FINISHED
Object FRM
FRM is the National Rail station code for Fareham railway station in Hampshire, England.
 E613737 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: FRM | Statement: [Fareham railway station, stationCode, FRM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: FRM
Context triple: [Fareham railway station, stationCode, FRM]
  • A. Man FRM
    Man FRM is an investment management subsidiary of Man Group specializing in systematic and quantitative trading strategies.
  • B. CFA
    CFA is the abbreviation for Commander Field Army, the senior British Army officer responsible for commanding the Field Army’s operational forces.
  • C. CFA
    CFA is the commonly used symbol for the West African CFA franc, a currency used by several West African countries.
  • D. FIN
    FIN is the three-letter ISO 3166-1 alpha-3 country code that uniquely identifies Finland in international standards and data systems.
  • E. FIN
    FIN is the commonly used abbreviation for the Department of Finance Canada, the federal government department responsible for developing economic, fiscal, and tax policy.
  • 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: FRM
Triple: [Fareham railway station, stationCode, FRM]
Generated description
FRM is the National Rail station code for Fareham railway station in Hampshire, England.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: FRM
Target entity description: FRM is the National Rail station code for Fareham railway station in Hampshire, England.
  • A. Man FRM
    Man FRM is an investment management subsidiary of Man Group specializing in systematic and quantitative trading strategies.
  • B. CFA
    CFA is the commonly used symbol for the West African CFA franc, a currency used by several West African countries.
  • C. CFA
    CFA is the abbreviation for Commander Field Army, the senior British Army officer responsible for commanding the Field Army’s operational forces.
  • D. FIN
    FIN is the three-letter ISO 3166-1 alpha-3 country code that uniquely identifies Finland in international standards and data systems.
  • E. FIN
    FIN is the commonly used abbreviation for the Department of Finance Canada, the federal government department responsible for developing economic, fiscal, and tax policy.
  • 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_69c68808d8d8819087369015270788fe completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d1049b7c8190a970a165d15b440b completed March 27, 2026, 6:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7008e6b308190a3d5db2bf4a469c4 completed March 27, 2026, 10:11 p.m.
NEDg Description generation batch_69c701be78cc8190a0848ea60908d129 completed March 27, 2026, 10:16 p.m.
NED2 Entity disambiguation (via description) batch_69c7021b27288190866aef500198479d completed March 27, 2026, 10:18 p.m.
Created at: March 27, 2026, 2:06 p.m.