Triple
T18848755
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prazeres |
E460984
|
entity |
| Predicate | isEndpointOf |
P390
|
FINISHED |
| Object | Tram 28 route |
—
|
NE NERFINISHED |
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 28 route | Statement: [Prazeres, isEndpointOf, Tram 28 route]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tram 28 route Context triple: [Prazeres, isEndpointOf, Tram 28 route]
-
A.
Tram 28 route
chosen
The Tram 28 route is a historic Lisbon tram line famed for its vintage yellow trams and scenic journey through the city’s oldest neighborhoods, including Alfama.
-
B.
Tram line 25
Tram line 25 is a Dutch tram route that connects Amsterdam with the nearby municipality of Amstelveen as part of the region’s public transport network.
-
C.
Tram 12
Tram 12 is a major tram line in Geneva’s public transport system, connecting key neighborhoods and suburbs across the city.
-
D.
Tram 17
Tram 17 is a tram line in Geneva’s public transport system operated by the city’s transit authority.
-
E.
Tram 15
Tram 15 is a major tram line in Geneva’s public transport system, connecting key districts across the city and its suburbs.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8dcfa11e4819090ab1ef5bdcd2b2e |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5b8f079b881908759135c5e2619ee |
completed | April 20, 2026, 5:26 a.m. |
Created at: April 10, 2026, 11:56 a.m.