Triple
T17570885
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lanark railway station |
E427932
|
entity |
| Predicate | stationCode |
P1289
|
FINISHED |
| Object |
LNK
LNK is the National Rail station code for Lanark railway station in South Lanarkshire, Scotland.
|
E794854
|
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: LNK | Statement: [Lanark railway station, stationCode, LNK]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: LNK Context triple: [Lanark railway station, stationCode, LNK]
-
A.
LNK
LNK is the three-letter IATA airport code for Lincoln Airport in Lincoln, Nebraska, USA.
-
B.
LKN
LKN is the IATA airport code for Leknes Airport, a regional airport serving the town of Leknes in Norway’s Lofoten archipelago.
-
C.
KLNK
KLNK is the ICAO airport code for Lincoln Airport, a public airfield serving Lincoln, Nebraska, in the United States.
-
D.
LINK
LINK is the radio callsign used by the Irish regional airline Airlink for air traffic control communications.
-
E.
NLNK
NLNK is the stock ticker symbol for NewLink Genetics, a biotechnology company focused on developing immuno-oncology therapies.
- 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: LNK Triple: [Lanark railway station, stationCode, LNK]
Generated description
LNK is the National Rail station code for Lanark railway station in South Lanarkshire, Scotland.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: LNK Target entity description: LNK is the National Rail station code for Lanark railway station in South Lanarkshire, Scotland.
-
A.
LNK
chosen
LNK is the three-letter IATA airport code for Lincoln Airport in Lincoln, Nebraska, USA.
-
B.
LKN
LKN is the IATA airport code for Leknes Airport, a regional airport serving the town of Leknes in Norway’s Lofoten archipelago.
-
C.
KLNK
KLNK is the ICAO airport code for Lincoln Airport, a public airfield serving Lincoln, Nebraska, in the United States.
-
D.
LINK
LINK is the radio callsign used by the Irish regional airline Airlink for air traffic control communications.
-
E.
NLNK
NLNK is the stock ticker symbol for NewLink Genetics, a biotechnology company focused on developing immuno-oncology therapies.
- 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_69d889e0385081908a04b66f4dd4bd0d |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e45930b0748190b55b95c523c47460 |
completed | April 19, 2026, 4:25 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a01dde64fd48190bcc55054d12d652a |
completed | May 11, 2026, 1:47 p.m. |
| NEDg | Description generation | batch_6a01df3e20708190a7ae2fdb52b12da7 |
completed | May 11, 2026, 1:53 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a01e0075f7c819097a3459dc5c703b6 |
completed | May 11, 2026, 1:56 p.m. |
Created at: April 10, 2026, 5:50 a.m.