Triple
T8975379
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Évry-Courcouronnes |
E214372
|
entity |
| Predicate | previouslyContainedEntity |
P79922
|
FINISHED |
| Object | commune of Évry |
—
|
LITERAL 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: commune of Évry | Statement: [Évry-Courcouronnes, previouslyContainedEntity, commune of Évry]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previouslyContainedEntity Context triple: [Évry-Courcouronnes, previouslyContainedEntity, commune of Évry]
-
A.
previouslyContained
chosen
Indicates that one entity was contained within another entity at some point in the past, but is not necessarily contained there now.
-
B.
previouslyContainedRegion
Indicates that one region used to spatially contain another region at some earlier time, but does not necessarily do so now.
-
C.
previouslyContainedCity
Indicates that one location used to include a particular city within its boundaries or jurisdiction at some time in the past, but no longer does.
-
D.
replacedEntity
Indicates that one entity has been substituted for, or taken the place of, another entity in a given context.
-
E.
isFormerEntity
Indicates that an entity previously held a particular status, role, or identity but no longer does so.
- 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_69ca839dbf608190a2f5990477115d29 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6784d1808190899c980f76084ff8 |
completed | April 1, 2026, 12:32 a.m. |
| PD | Predicate disambiguation | batch_69cc5ed9a2d48190ad11381078e823b7 |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 7:02 p.m.