Triple
T9275066
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tartu railway station |
E222924
|
entity |
| Predicate | hasStationCode |
P1289
|
FINISHED |
| Object |
TRT
TRT is the station code for Tartu railway station, the main rail transport hub in the city of Tartu, Estonia.
|
E787952
|
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: TRT | Statement: [Tartu railway station, hasStationCode, TRT]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: TRT Context triple: [Tartu railway station, hasStationCode, TRT]
-
A.
TRT
TRT is Turkey's national public broadcaster, operating multiple television and radio channels domestically and internationally.
-
B.
TRT
TRT is the time zone used in Turkey, corresponding to UTC+3.
-
C.
TRTS
TRTS is the commonly used abbreviation for the Taipei Metro rapid transit system serving the Taipei metropolitan area in Taiwan.
-
D.
TRTA
TRTA (Teito Rapid Transit Authority) was the former public corporation responsible for operating most of Tokyo’s subway network before its privatization into Tokyo Metro.
-
E.
TRTA
TRTA is the acronym for the Tahoe Rim Trail Association, a nonprofit organization dedicated to building, maintaining, and promoting the Tahoe Rim Trail around Lake Tahoe.
- 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: TRT Triple: [Tartu railway station, hasStationCode, TRT]
Generated description
TRT is the station code for Tartu railway station, the main rail transport hub in the city of Tartu, Estonia.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: TRT Target entity description: TRT is the station code for Tartu railway station, the main rail transport hub in the city of Tartu, Estonia.
-
A.
TRT
TRT is the time zone used in Turkey, corresponding to UTC+3.
-
B.
TRT
TRT is Turkey's national public broadcaster, operating multiple television and radio channels domestically and internationally.
-
C.
TRTS
TRTS is the commonly used abbreviation for the Taipei Metro rapid transit system serving the Taipei metropolitan area in Taiwan.
-
D.
TRTA
TRTA (Teito Rapid Transit Authority) was the former public corporation responsible for operating most of Tokyo’s subway network before its privatization into Tokyo Metro.
-
E.
TRTA
TRTA is the acronym for the Tahoe Rim Trail Association, a nonprofit organization dedicated to building, maintaining, and promoting the Tahoe Rim Trail around Lake Tahoe.
- 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_69ca841ffe208190aa7bcffbef2f8379 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd078a045c8190b2c4d1ec64b932ad |
completed | April 1, 2026, 11:54 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d09c3dd140819099fc0e95c4d48ba9 |
completed | April 4, 2026, 5:06 a.m. |
| NEDg | Description generation | batch_69d09cf1f2f48190b53e062c3eb4565d |
completed | April 4, 2026, 5:09 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d09d9739d48190ac3b240390f36c38 |
completed | April 4, 2026, 5:11 a.m. |
Created at: March 30, 2026, 7:34 p.m.