Triple
T18988879
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tackley railway station |
E464628
|
entity |
| Predicate | stationCode |
P1289
|
FINISHED |
| Object |
TAC
TAC is the National Rail station code for Tackley railway station in Oxfordshire, England.
|
E1353613
|
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: TAC | Statement: [Tackley railway station, stationCode, TAC]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: TAC Context triple: [Tackley railway station, stationCode, TAC]
-
A.
TAC
TAC is the commonly used abbreviation for The Athletic Congress, the former governing body for track and field in the United States.
-
B.
TAC
TAC is the commonly used abbreviation for Tartu Art College, an Estonian institution of higher education specializing in art and design.
-
C.
US TAC
US TAC is the UN/LOCODE identifier assigned to the Port of Tacoma in Washington, United States, for international shipping and logistics.
-
D.
TAS
TAS is the commonly used French acronym for the Court of Arbitration for Sport, an international body that settles sports-related disputes through arbitration.
-
E.
TAS
TAS is the IATA airport code for Islam Karimov Tashkent International Airport, the main international gateway to Tashkent, Uzbekistan.
- 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: TAC Triple: [Tackley railway station, stationCode, TAC]
Generated description
TAC is the National Rail station code for Tackley railway station in Oxfordshire, England.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: TAC Target entity description: TAC is the National Rail station code for Tackley railway station in Oxfordshire, England.
-
A.
TAC
TAC is the commonly used abbreviation for The Athletic Congress, the former governing body for track and field in the United States.
-
B.
TAC
TAC is the commonly used abbreviation for Tartu Art College, an Estonian institution of higher education specializing in art and design.
-
C.
US TAC
US TAC is the UN/LOCODE identifier assigned to the Port of Tacoma in Washington, United States, for international shipping and logistics.
-
D.
TAS
TAS is the commonly used French acronym for the Court of Arbitration for Sport, an international body that settles sports-related disputes through arbitration.
-
E.
TAS
TAS is the IATA airport code for Islam Karimov Tashkent International Airport, the main international gateway to Tashkent, Uzbekistan.
- 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_69d8dd008af48190a97ff1c6488edf1b |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d66272388190850a7e5dec165a01 |
completed | April 20, 2026, 7:31 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a05b45340888190a21cea6e72b7facc |
completed | May 14, 2026, 11:38 a.m. |
| NEDg | Description generation | batch_6a05b62d8aec81908b71232f52eb3612 |
completed | May 14, 2026, 11:46 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a05b68aba3081908ca21d732e45f454 |
completed | May 14, 2026, 11:48 a.m. |
Created at: April 10, 2026, 12:01 p.m.