Triple
T16289027
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Île-de-France fare system |
E395467
|
entity |
| Predicate | usesZoning |
P122545
|
FINISHED |
| Object | Île-de-France fare zones |
—
|
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: Île-de-France fare zones | Statement: [Île-de-France fare system, usesZoning, Île-de-France fare zones]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesZoning Context triple: [Île-de-France fare system, usesZoning, Île-de-France fare zones]
-
A.
hasZoningApproach
Indicates the type or method of zoning policy or strategy that is applied to or associated with an entity.
-
B.
hasZoningPolicy
Indicates that a governing body or authority has established or adopted a specific zoning policy that regulates land use or development within its jurisdiction.
-
C.
zonedUse
Indicates the designated or permitted type of land use assigned to a property or area under zoning regulations.
-
D.
hasZoningRestriction
Indicates that an entity is subject to a specific zoning-related limitation or regulatory constraint.
-
E.
zonedTo
Indicates that one entity is assigned or designated to fall within the jurisdiction, service area, or regulatory zone of another entity.
- F. None of above. chosen
Provenance (4 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_69d87f22c7248190a54c949738441e2e |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e249165af881908ce44c4517c93c12 |
completed | April 17, 2026, 2:52 p.m. |
| PD | Predicate disambiguation | batch_69e219f68d308190b71c1601303f0628 |
completed | April 17, 2026, 11:31 a.m. |
| PDg | Predicate description generation | batch_69e21e56e0348190a3d9475360231a70 |
completed | April 17, 2026, 11:49 a.m. |
Created at: April 10, 2026, 5:05 a.m.