Triple
T29860195
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Couvent des Célestins, Paris |
E758290
|
entity |
| Predicate | formerLocationNow |
P197701
|
FINISHED |
| Object | Boulevard Henri-IV, Paris |
—
|
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: Boulevard Henri-IV, Paris | Statement: [Couvent des Célestins, Paris, formerLocationNow, Boulevard Henri-IV, Paris]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerLocationNow Context triple: [Couvent des Célestins, Paris, formerLocationNow, Boulevard Henri-IV, Paris]
-
A.
formerLocationState
Indicates that an entity was previously located in, based in, or associated with a particular state, but is no longer there.
-
B.
formerlyKnownLocationAs
Indicates that an entity was previously known or referred to by a different location name or designation.
-
C.
previousLocationName
Indicates that one entity specifies the name of a location where another entity was situated or occurred before its current location.
-
D.
locationNowUsedAs
Indicates that a location is currently being used or repurposed for a particular function, activity, or entity.
-
E.
formerlyLocatedOn
Indicates that an entity was once located on or situated upon another entity, but is no longer in that position.
- F. None of above. chosen
Provenance (4 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_69f2245b4dec8190b85f664d918a00a5 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69fea2d0a4d08190aa06aeb902a02d5a |
completed | May 9, 2026, 2:58 a.m. |
| PD | Predicate disambiguation | batch_69fea24698348190b9b992a8e7cdbcd0 |
completed | May 9, 2026, 2:56 a.m. |
| PDg | Predicate description generation | batch_69fea2cfcd648190a15e5b90889095b1 |
completed | May 9, 2026, 2:58 a.m. |
Created at: April 29, 2026, 5:48 p.m.