Triple
T4036878
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zermatt |
E83847
|
entity |
| Predicate | localTransport |
P11571
|
FINISHED |
| Object | electric taxis |
—
|
LITERAL 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: electric taxis | Statement: [Zermatt, localTransport, electric taxis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: localTransport Context triple: [Zermatt, localTransport, electric taxis]
-
A.
usesTransport
chosen
Indicates that an entity employs or relies on a particular mode or means of transportation to move from one place to another.
-
B.
transportLayerFor
Indicates that one entity functions as the transport-layer protocol or mechanism used to carry or deliver another entity’s data.
-
C.
transportProtocol
Indicates the communication protocol used to transport data between entities in a networked interaction.
-
D.
hasApproximateTransport
Indicates that one entity is connected to another by a transport option whose route, timing, or characteristics are similar to, but not exactly the same as, a referenced or ideal transport connection.
-
E.
allowedTransport
Indicates that a particular mode or means of transport is permitted for use between the related entities.
- F. None of above.
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_69aed92f7cf0819098e0539bdcc3767f |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefb349e648190b9f227df4cd76fa0 |
completed | March 9, 2026, 4:54 p.m. |
| PD | Predicate disambiguation | batch_69aef8fe440c819093a7fa22c4ff3f1a |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:36 p.m.