Triple
T32719413
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | La Défense RER station |
E836627
|
entity |
| Predicate | hasAdjacentStationOnRERA |
P181057
|
FINISHED |
| Object | Charles de Gaulle – Étoile |
—
|
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: Charles de Gaulle – Étoile | Statement: [La Défense RER station, hasAdjacentStationOnRERA, Charles de Gaulle – Étoile]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAdjacentStationOnRERA Context triple: [La Défense RER station, hasAdjacentStationOnRERA, Charles de Gaulle – Étoile]
-
A.
hasAdjacentStationOnAC
Indicates that one station is directly next to another station along the AC line or route.
-
B.
hasAdjacentStationOnIND
Indicates that one station is directly next to another station on the IND (Independent Subway System) line, with no other stations in between.
-
C.
hasAdjacentStationOnE
Indicates that one station is directly adjacent to another station on the east side.
-
D.
hasAdjacentStations
chosen
Indicates that two stations are directly next to each other in a sequence or network, with no other station in between.
-
E.
hasAdjacentStationOnL
Indicates that one station is directly next to another station along line L in the network.
- 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_69f34935455881909088975d79460418 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fd35d108908190b79b1e8e6bbd62aa |
completed | May 8, 2026, 1:01 a.m. |
| PD | Predicate disambiguation | batch_69fd34cb46108190b43c3b7f67ec4cd4 |
completed | May 8, 2026, 12:56 a.m. |
Created at: May 1, 2026, 1:11 a.m.