Triple
T29589518
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TER Basse-Normandie |
E754113
|
entity |
| Predicate | providedConnectionTo |
P37306
|
FINISHED |
| Object | Intercités services |
—
|
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: Intercités services | Statement: [TER Basse-Normandie, providedConnectionTo, Intercités services]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: providedConnectionTo Context triple: [TER Basse-Normandie, providedConnectionTo, Intercités services]
-
A.
plannedToBeConnectedTo
Indicates that one entity is intended or scheduled to be linked or joined with another entity in the future.
-
B.
connectionTo
chosen
Indicates a relationship in which one entity is linked, associated, or otherwise related to another entity.
-
C.
reportedConnection
Indicates that a relationship or link between entities has been asserted or documented by some source, but may not be independently verified.
-
D.
compatibleConnection
Indicates that two entities can be connected or used together without conflict, supporting proper operation or interaction.
-
E.
helpedConnect
Indicates that one entity assisted in establishing or facilitating a connection or relationship between two or more other entities.
- 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_69f0ef836ac88190bd809dc58b5ec907 |
completed | April 28, 2026, 5:33 p.m. |
| NER | Named-entity recognition | batch_69fd02680d948190a3463fb119ba8556 |
completed | May 7, 2026, 9:21 p.m. |
| PD | Predicate disambiguation | batch_69fcf89c69b4819082bbc564bd15137d |
completed | May 7, 2026, 8:39 p.m. |
Created at: April 28, 2026, 6:13 p.m.