Triple
T27171039
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mont d’Ambin Base Tunnel |
E682909
|
entity |
| Predicate | operatorProject |
P144535
|
FINISHED |
| Object | Lyon Turin Ferroviaire |
—
|
NE NERFINISHED |
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: Lyon Turin Ferroviaire | Statement: [Mont d’Ambin Base Tunnel, operatorProject, Lyon Turin Ferroviaire]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatorProject Context triple: [Mont d’Ambin Base Tunnel, operatorProject, Lyon Turin Ferroviaire]
-
A.
operatorTask
Indicates that an operator is responsible for performing or managing a specific task.
-
B.
operationOf
Indicates that one entity is the function, activity, or process carried out by another entity (such as a system, device, or organization).
-
C.
operatorPlanned
Indicates that an operator has scheduled or arranged a specific action, process, or operation to occur.
-
D.
projectOperated
chosen
Indicates that a project is actively run, managed, or carried out by a particular agent or organization.
-
E.
operator
Indicates that one entity functions as the operator (controller or handler) of another entity, such as a system, device, or process.
- 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_69eefacf6e788190a75a64399d9e3109 |
completed | April 27, 2026, 5:57 a.m. |
| NER | Named-entity recognition | batch_69fdb31800508190beec15adb9bbd292 |
completed | May 8, 2026, 9:55 a.m. |
| PD | Predicate disambiguation | batch_69fdb19c381c8190bafb2f565da097f1 |
completed | May 8, 2026, 9:49 a.m. |
Created at: April 27, 2026, 9:23 a.m.