Triple
T10575375
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | T3 |
E249596
|
entity |
| Predicate | operatedBy |
P86
|
FINISHED |
| Object | TRAM |
E249591
|
NE FINISHED |
How this triple was built (2 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: TRAM | Statement: [T3, operatedBy, TRAM]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: TRAM Context triple: [T3, operatedBy, TRAM]
-
A.
TRAM
chosen
TRAM is the public tramway operator that manages several modern light rail lines in the Barcelona metropolitan area.
-
B.
TRAX
TRAX is the light rail system serving the Salt Lake City metropolitan area along Utah’s Wasatch Front.
-
C.
Tramazul
Tramazul is a conceptual artwork by Brazilian artist Regina Silveira, known for its striking use of blue tape to create large-scale, illusionistic spatial distortions.
-
D.
Transtu
Transtu is the public transport authority in Tunis responsible for operating the city’s metro and other urban transit services.
-
E.
Traficom
Traficom is Finland’s national authority responsible for regulating and overseeing transport and communications services, infrastructure, and safety.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d381c8bd708190acf3d275c908251e |
completed | April 6, 2026, 9:50 a.m. |
| NER | Named-entity recognition | batch_69d5274b100c8190b477ef4cb745c269 |
completed | April 7, 2026, 3:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d97a1bba1c8190af5a078f40f3bc0a |
completed | April 10, 2026, 10:30 p.m. |
Created at: April 6, 2026, 12:38 p.m.