Triple
T6718680
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stonehaven railway station |
E153337
|
entity |
| Predicate | hasStationCode |
P1289
|
FINISHED |
| Object |
STN
STN is the National Rail station code for Stonehaven railway station in Aberdeenshire, Scotland.
|
E614523
|
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: STN | Statement: [Stonehaven railway station, hasStationCode, STN]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: STN Context triple: [Stonehaven railway station, hasStationCode, STN]
-
A.
STN
STN is the three-letter IATA airport code for London Stansted Airport, a major international airport serving the London area in the United Kingdom.
-
B.
STN
STN is the currency code for the São Tomé and Príncipe dobra, the official monetary unit of São Tomé and Príncipe.
-
C.
STN International
STN International is a professional online scientific and technical information service widely used for advanced literature and patent searching in chemistry and related fields.
-
D.
STC
STC is the commonly used abbreviation for RAF Strike Command, the former major operational command of the Royal Air Force responsible for the UK’s air combat forces.
-
E.
STC
STC is the acronym commonly used for Mexico City’s Sistema de Transporte Colectivo, the public agency that operates the city’s metro system.
- 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: STN Triple: [Stonehaven railway station, hasStationCode, STN]
Generated description
STN is the National Rail station code for Stonehaven railway station in Aberdeenshire, Scotland.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: STN Target entity description: STN is the National Rail station code for Stonehaven railway station in Aberdeenshire, Scotland.
-
A.
STN
STN is the three-letter IATA airport code for London Stansted Airport, a major international airport serving the London area in the United Kingdom.
-
B.
STN
STN is the currency code for the São Tomé and Príncipe dobra, the official monetary unit of São Tomé and Príncipe.
-
C.
STN International
STN International is a professional online scientific and technical information service widely used for advanced literature and patent searching in chemistry and related fields.
-
D.
STC
STC is the commonly used abbreviation for RAF Strike Command, the former major operational command of the Royal Air Force responsible for the UK’s air combat forces.
-
E.
STC
STC is the acronym commonly used for Mexico City’s Sistema de Transporte Colectivo, the public agency that operates the city’s metro system.
- 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_69c68809b4608190a2509ddb5ab87f05 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d135d27c819088c45839ad0e7bab |
completed | March 27, 2026, 6:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7009b9b64819095ae1a65cd72c374 |
completed | March 27, 2026, 10:11 p.m. |
| NEDg | Description generation | batch_69c705220cb0819081a70175c150d138 |
completed | March 27, 2026, 10:30 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c705db3098819083ce9a93e429b758 |
completed | March 27, 2026, 10:34 p.m. |
Created at: March 27, 2026, 2:07 p.m.