Triple
T28561524
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paris Métro Line 3bis |
E722556
|
entity |
| Predicate | operatesWithinFareZone |
P844
|
FINISHED |
| Object | Paris fare zone 1 |
—
|
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: Paris fare zone 1 | Statement: [Paris Métro Line 3bis, operatesWithinFareZone, Paris fare zone 1]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatesWithinFareZone Context triple: [Paris Métro Line 3bis, operatesWithinFareZone, Paris fare zone 1]
-
A.
hasFareZone
chosen
Indicates that an entity is located within or associated with a specific fare zone used for pricing or ticketing.
-
B.
fareZoneIncludes
Indicates that a specified fare zone geographically or logically contains a given location, stop, or segment for fare calculation purposes.
-
C.
hasFareZoneSystem
Indicates that an entity uses or is associated with a particular fare zone system for determining travel costs or ticketing.
-
D.
hasFareZoneFeature
Indicates that an entity is associated with a specific fare zone or fare-related area designation.
-
E.
fareZoneOfStationIdentified
Indicates that the specific fare zone associated with a given station has been identified.
- 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_69f01a5f69d08190ad5c0d2167078dec |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69fea1f5d8c481908dc3351dc9ecef7f |
completed | May 9, 2026, 2:54 a.m. |
| PD | Predicate disambiguation | batch_69fea06b6fe0819095bf4c1bc9809927 |
completed | May 9, 2026, 2:48 a.m. |
Created at: April 28, 2026, 4:05 a.m.