Triple
T4330718
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Réunion |
E96740
|
entity |
| Predicate | hasAirport |
P105
|
FINISHED |
| Object | Roland Garros Airport |
E153258
|
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: Roland Garros Airport | Statement: [Réunion, hasAirport, Roland Garros Airport]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Roland Garros Airport Context triple: [Réunion, hasAirport, Roland Garros Airport]
-
A.
Roland Garros Airport
chosen
Roland Garros Airport is the main international airport on the French island of Réunion in the Indian Ocean.
-
B.
Charles de Gaulle Airport
Charles de Gaulle Airport is the largest international airport in France and a major European aviation hub serving the Paris metropolitan area.
-
C.
Paris–Le Bourget Airport
Paris–Le Bourget Airport is a historic airport near Paris that now primarily serves business aviation and hosts the biennial Paris Air Show.
-
D.
Lyon–Saint-Exupéry Airport
Lyon–Saint-Exupéry Airport is a major international airport in eastern France serving the city of Lyon and the surrounding Auvergne-Rhône-Alpes region.
-
E.
Paris Orly Airport
Paris Orly Airport is a major international airport serving the Paris metropolitan area, located south of the city and handling a large share of its domestic and European flights.
- 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_69b34542fd908190b11b08faad8decfd |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b3514c39748190900e13e70ed8848c |
completed | March 12, 2026, 11:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bdacc9ef8c81909ff2a16cf68844d0 |
completed | March 20, 2026, 8:23 p.m. |
Created at: March 12, 2026, 11:13 p.m.