Triple
T16367124
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rio–Antirrio Bridge |
E397464
|
entity |
| Predicate | mainContractor |
P7138
|
FINISHED |
| Object | VINCI Construction |
E1012380
|
NE 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: VINCI Construction | Statement: [Rio–Antirrio Bridge, mainContractor, VINCI Construction]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: VINCI Construction Context triple: [Rio–Antirrio Bridge, mainContractor, VINCI Construction]
-
A.
Eiffage
Eiffage is a major French construction and civil engineering company known for delivering large-scale infrastructure projects such as the Millau Viaduct.
-
B.
Vinci Construction
chosen
Vinci Construction is a major global construction and civil engineering company specializing in large-scale infrastructure and building projects.
-
C.
Strabag
Strabag is a major European construction company based in Austria, known for large-scale infrastructure, civil engineering, and building projects across numerous countries.
-
D.
Vinci SA
Vinci SA is a major French multinational concessions and construction company specializing in infrastructure development and management worldwide.
-
E.
Longvic
Longvic is a commune in eastern France’s Côte-d’Or department, forming part of the suburban area just southeast of the city of Dijon.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d87f2778dc8190aa95c7572db127e6 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2ff3de3d88190a42cd708746c8bd0 |
completed | April 18, 2026, 3:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a002dc29f088190ba5d69ff3c12a251 |
completed | May 10, 2026, 7:03 a.m. |
Created at: April 10, 2026, 5:08 a.m.