Triple
T10982621
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Autoroute A13 |
E259545
|
entity |
| Predicate | isFreeSection |
P30349
|
FINISHED |
| Object | Paris–Mantes-la-Jolie urban section |
—
|
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–Mantes-la-Jolie urban section | Statement: [Autoroute A13, isFreeSection, Paris–Mantes-la-Jolie urban section]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isFreeSection Context triple: [Autoroute A13, isFreeSection, Paris–Mantes-la-Jolie urban section]
-
A.
freeSection
chosen
Indicates that a section or segment is available without cost or restrictions to the user.
-
B.
isFreeToUse
Indicates that something can be used without cost, restriction, or required permission.
-
C.
hasFreeZone
Indicates that an entity includes or is associated with a designated free zone area where special rules, privileges, or exemptions apply.
-
D.
isFreeToEdit
Indicates that an entity has permission or the ability to modify or update another entity without restriction.
-
E.
isFreeToRead
Indicates that access to the referenced content or resource does not require payment and can be read without cost.
- 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_69d6aa895f4c8190887a15460ef622f4 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d772eb518c8190a885a417815f2ff6 |
completed | April 9, 2026, 9:35 a.m. |
| PD | Predicate disambiguation | batch_69d72e9055908190b438f039574aaaaf |
completed | April 9, 2026, 4:44 a.m. |
Created at: April 8, 2026, 9:24 p.m.