Triple
T3173401
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paris Métro Line 6 |
E66406
|
entity |
| Predicate | locationInCity |
P40
|
FINISHED |
| Object | southern Paris |
—
|
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: southern Paris | Statement: [Paris Métro Line 6, locationInCity, southern Paris]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locationInCity Context triple: [Paris Métro Line 6, locationInCity, southern Paris]
-
A.
isInCity
Indicates that one entity is located within the geographical boundaries of a specified city.
-
B.
cityLocatedIn
Indicates that a city is geographically situated within a specified larger administrative or territorial region.
-
C.
locatedIn
chosen
Indicates that one entity exists or is situated within the spatial, administrative, or conceptual boundaries of another entity.
-
D.
basedInCity
Indicates that an entity has its primary location, headquarters, or main operations situated in a specified city.
-
E.
locatedInPlannedCity
Indicates that something is situated within the boundaries of a city that was deliberately designed and planned rather than having developed organically.
- 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_69ad8586a34c8190944c63ec11a8de1a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada66facf881908b9ec687d68ce91b |
completed | March 8, 2026, 4:40 p.m. |
| PD | Predicate disambiguation | batch_69ad9e0076b4819094628f1ad10b8f68 |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:06 p.m.