Triple
T33911508
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paris–Cairo |
E869326
|
entity |
| Predicate | servedFromAirport |
P101128
|
FINISHED |
| Object | Paris Charles de Gaulle Airport |
—
|
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: Paris Charles de Gaulle Airport | Statement: [Paris–Cairo, servedFromAirport, Paris Charles de Gaulle Airport]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servedFromAirport Context triple: [Paris–Cairo, servedFromAirport, Paris Charles de Gaulle Airport]
-
A.
servedByAirportInOriginCity
Indicates that the origin city of a trip or route is served by a particular airport.
-
B.
servesAirport
Indicates that a transportation service or route provides access to and operates for a particular airport.
-
C.
hasOriginAirport
chosen
Indicates that something, typically a flight or journey, departs from or is associated with a specific origin airport.
-
D.
airportServed
Indicates that a particular airport provides service to, or is used for air travel to and from, a given location or area.
-
E.
servesAirportIATA
Indicates that a transportation service or facility operates routes to or from the airport identified by the given IATA code.
- 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_69f3499869bc8190b6c33a81686af226 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69ff7595c9bc8190982c6e6e07a0c78f |
completed | May 9, 2026, 5:57 p.m. |
| PD | Predicate disambiguation | batch_69ff715432a88190a25670d26614bde2 |
completed | May 9, 2026, 5:39 p.m. |
Created at: May 1, 2026, 1:48 a.m.