Triple
T6838733
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Avignon TGV station |
E157515
|
entity |
| Predicate | nearbyAirportConnection |
P23780
|
FINISHED |
| Object | Marseille Provence Airport via TGV |
—
|
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: Marseille Provence Airport via TGV | Statement: [Avignon TGV station, nearbyAirportConnection, Marseille Provence Airport via TGV]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nearbyAirportConnection Context triple: [Avignon TGV station, nearbyAirportConnection, Marseille Provence Airport via TGV]
-
A.
nearestAirport
Indicates that one airport is the closest in distance to a given location or entity compared to all other airports.
-
B.
nearbyAirportTerminal
Indicates that one airport terminal is located close to another airport terminal in physical space.
-
C.
airportLocatedNear
Indicates that an airport is situated close to a specified place or geographic feature.
-
D.
associatedAirport
Indicates a relationship where an entity is linked or connected to a specific airport, typically as its relevant or corresponding airport.
-
E.
connectsWithAirport
chosen
Indicates that there is a direct transportation or operational link established between an entity and an airport.
- 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_69c6882c53608190b99aebef079b23bd |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d67ee1c88190b82a9b6b3d1e3875 |
completed | March 27, 2026, 7:11 p.m. |
| PD | Predicate disambiguation | batch_69c6d09f90648190bc0a462c7d59de1b |
completed | March 27, 2026, 6:46 p.m. |
Created at: March 27, 2026, 2:19 p.m.