Triple
T27831862
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Noisy–Champs station |
E703122
|
entity |
| Predicate | futurePartOfNetwork |
P42365
|
FINISHED |
| Object | Grand Paris Express |
—
|
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: Grand Paris Express | Statement: [Noisy–Champs station, futurePartOfNetwork, Grand Paris Express]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: futurePartOfNetwork Context triple: [Noisy–Champs station, futurePartOfNetwork, Grand Paris Express]
-
A.
laterNetwork
Indicates that one network occurs or is established after another network in time.
-
B.
partOfNetworkExpansion
Indicates that an entity participates in or contributes to the growth or extension of a larger network.
-
C.
networkPartOf
Indicates that one network is a component or subdivision of a larger, encompassing network.
-
D.
futureComponentOf
chosen
Indicates that one entity is expected or planned to become a component or part of another entity at some point in the future.
-
E.
futureSiteOf
Indicates that a location is planned or designated to become the site of a particular entity or structure in the future.
- 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_69ef840b94b08190950a4f77296938b2 |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_69f6389cf96c8190a045e3c53f83f3cd |
completed | May 2, 2026, 5:47 p.m. |
| PD | Predicate disambiguation | batch_69f6318ae6f08190b3f85f9201046a15 |
completed | May 2, 2026, 5:16 p.m. |
Created at: April 27, 2026, 5:56 p.m.