Triple
T27171123
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TELT |
E682911
|
entity |
| Predicate | projectInvolves |
P82597
|
FINISHED |
| Object | Mont Cenis base tunnel |
—
|
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: Mont Cenis base tunnel | Statement: [TELT, projectInvolves, Mont Cenis base tunnel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: projectInvolves Context triple: [TELT, projectInvolves, Mont Cenis base tunnel]
-
A.
intendedProject
Indicates that an entity is the planned or targeted project associated with another entity (such as a person, organization, or activity).
-
B.
hasProject
Indicates that an entity is associated with or responsible for a particular project.
-
C.
collaborativeProjects
Indicates that two or more entities work together on shared projects or initiatives toward common goals.
-
D.
isOnProject
chosen
Indicates that an entity is currently assigned to, involved with, or working on a particular project.
-
E.
projectsOn
Indicates that one entity casts, directs, or extends itself onto the surface, area, or domain of another entity.
- 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_69f62cd2ceb481908cd9fae52a542206 |
completed | May 2, 2026, 4:56 p.m. |
| PD | Predicate disambiguation | batch_69f62c1762f881908c25e8f70ecd5041 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 9:23 a.m.