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.