Triple
T2247123
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | A86 autoroute |
E49528
|
entity |
| Predicate | tunnelSectionLocation |
P11383
|
FINISHED |
| Object | between Rueil-Malmaison and Vélizy-Villacoublay |
—
|
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: between Rueil-Malmaison and Vélizy-Villacoublay | Statement: [A86 autoroute, tunnelSectionLocation, between Rueil-Malmaison and Vélizy-Villacoublay]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tunnelSectionLocation Context triple: [A86 autoroute, tunnelSectionLocation, between Rueil-Malmaison and Vélizy-Villacoublay]
-
A.
tunnelCircumference
Indicates the circular distance around the inner boundary of a tunnel’s cross-section.
-
B.
tunnelType
Indicates the specific kind or classification of a tunnel associated with an entity.
-
C.
locationOfPassage
chosen
Indicates the place or area through which a passage, route, or transit occurs or is situated.
-
D.
tracksSector
Indicates that one entity monitors, follows, or keeps records of the status or performance of a particular sector.
-
E.
hasTunnelLengthApprox
Indicates that an entity has a tunnel whose length is approximately a specified value.
- 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_69a88aa979788190ad6500f1d8eee2fc |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc0ec46b08190ae12de8b255eb71d |
completed | March 7, 2026, 6:08 a.m. |
| PD | Predicate disambiguation | batch_69abbdb160248190aa75b38f11ad8602 |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:47 p.m.