Triple
T12587192
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | West Midlands Metro |
E300495
|
entity |
| Predicate | usesRollingStock |
P5426
|
FINISHED |
| Object | CAF Urbos 3 tram |
E247343
|
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: CAF Urbos 3 tram | Statement: [West Midlands Metro, usesRollingStock, CAF Urbos 3 tram]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CAF Urbos 3 tram Context triple: [West Midlands Metro, usesRollingStock, CAF Urbos 3 tram]
-
A.
CAF Urbos 3 trams
CAF Urbos 3 trams are modern low-floor light rail vehicles manufactured by CAF and used in urban tram and light rail systems worldwide.
-
B.
Alstom Citadis tram
The Alstom Citadis tram is a family of modern low-floor light rail vehicles widely used in urban tram networks around the world.
-
C.
CAF Urbos 3
chosen
The CAF Urbos 3 is a modern low-floor light rail tram model built by Spanish manufacturer CAF and used in various urban tram systems worldwide.
-
D.
CAF A35 tram
The CAF A35 tram is a modern low-floor light rail vehicle built by Spanish manufacturer CAF, used on Stockholm’s contemporary tram and light rail lines.
-
E.
Tram 2000
Tram 2000 is a series of articulated light rail vehicles used for urban public transport in Zürich, Switzerland.
- 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_69d7bde87b648190bcd0266e9efde098 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d954bbe72c8190aa11090bb6b480c9 |
completed | April 10, 2026, 7:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f65ebed164819083fbdaa775a59cd4 |
completed | May 2, 2026, 8:29 p.m. |
Created at: April 9, 2026, 5:05 p.m.