Triple
T13324573
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beauvais–Tillé Airport |
E317404
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Tillé |
E317403
|
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: Tillé | Statement: [Beauvais–Tillé Airport, locatedNear, Tillé]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tillé Context triple: [Beauvais–Tillé Airport, locatedNear, Tillé]
-
A.
Tillé
chosen
Tillé is a commune in northern France best known for hosting Beauvais–Tillé Airport, a secondary hub for low-cost flights serving the Paris region.
-
B.
Sille
Sille is a historic village near Konya in central Turkey, known for its ancient rock-cut architecture and long-standing Greek Orthodox and Turkish cultural heritage.
-
C.
Graslei
Graslei is a historic quay along the Leie River in the center of Ghent, Belgium, renowned for its picturesque row of medieval guild houses and vibrant café culture.
-
D.
Arvieu
Arvieu is a rural commune in the Aveyron department of southern France, known for its scenic setting on the Lévézou plateau near major lakes and its traditional agricultural character.
-
E.
Tilion
Tilion is a Maia from J.R.R. Tolkien’s legendarium who became the steersman of the Moon, guiding its course across the sky.
- 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_69d806b4d62c81908d4ced1665414be5 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d9992c1fec8190bcb6a6bb3c973a24 |
completed | April 11, 2026, 12:43 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7266cfb3c8190ac9ccb7696d02922 |
completed | May 3, 2026, 10:41 a.m. |
Created at: April 9, 2026, 9:30 p.m.