Triple

T19080123
Position Surface form Disambiguated ID Type / Status
Subject Porth railway station E467005 entity
Predicate stationCode P1289 FINISHED
Object POR
POR is the National Rail station code for Porth railway station in Rhondda Cynon Taf, Wales.
 E1356538 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: POR | Statement: [Porth railway station, stationCode, POR]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: POR
Context triple: [Porth railway station, stationCode, POR]
  • A. POR
    POR is the standard abbreviation used for the Portland Sea Dogs Minor League Baseball team.
  • B. POR
    POR is the three-letter FIFA country code used to represent the Portugal national football team in international competitions and rankings.
  • C. PAR
    PAR is the IATA city code representing the collective airport system serving Paris, France, including major airports such as Charles de Gaulle and Orly.
  • D. PAR
    PAR is the standard abbreviation used for the Parramatta Eels, a professional rugby league club based in Sydney, Australia.
  • E. PAR
    PAR is a keyword in the Occam programming language used to specify that a group of processes should execute concurrently.
  • 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: POR
Triple: [Porth railway station, stationCode, POR]
Generated description
POR is the National Rail station code for Porth railway station in Rhondda Cynon Taf, Wales.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: POR
Target entity description: POR is the National Rail station code for Porth railway station in Rhondda Cynon Taf, Wales.
  • A. POR
    POR is the three-letter FIFA country code used to represent the Portugal national football team in international competitions and rankings.
  • B. POR
    POR is the standard abbreviation used for the Portland Sea Dogs Minor League Baseball team.
  • C. PAR
    PAR is the IATA city code representing the collective airport system serving Paris, France, including major airports such as Charles de Gaulle and Orly.
  • D. PAR
    PAR is the standard abbreviation used for the Parramatta Eels, a professional rugby league club based in Sydney, Australia.
  • E. PAR
    PAR is a keyword in the Occam programming language used to specify that a group of processes should execute concurrently.
  • 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_69d8dd04f4488190b1121cc53ef2bfd6 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e2e82ec08190873186ff51e89d86 completed April 20, 2026, 8:25 a.m.
NED1 Entity disambiguation (via context triple) batch_6a05d3641f608190a8f849304e52f203 completed May 14, 2026, 1:51 p.m.
NEDg Description generation batch_6a05d421965c8190b6f44aa2c8df5150 completed May 14, 2026, 1:54 p.m.
NED2 Entity disambiguation (via description) batch_6a05d49f62f881908ca289b644f29a53 completed May 14, 2026, 1:56 p.m.
Created at: April 10, 2026, 12:04 p.m.