Triple
T8832872
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chaise cassée |
E210186
|
entity |
| Predicate | reinstalled |
P12197
|
FINISHED |
| Object | 2007 |
—
|
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: 2007 | Statement: [Chaise cassée, reinstalled, 2007]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reinstalled Context triple: [Chaise cassée, reinstalled, 2007]
-
A.
reintroduced
Indicates that an entity that was previously removed, extinct, or absent has been brought back or restored to a place, context, or state.
-
B.
rebootOf
Indicates that one work is a new version that restarts or reimagines the story, continuity, or franchise of another earlier work.
-
C.
re-establishedAfter
Indicates that a relationship or state was previously ended or inactive and then brought back into effect following a specified event or time.
-
D.
recommissioned
chosen
Indicates that something previously deactivated, retired, or out of service has been restored and formally returned to active use or operation.
-
E.
relaunch
Indicates restarting or bringing back into operation something that was previously launched, often with changes or improvements.
- 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_69ca8388549c819095fd94eadefbb007 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc605005788190a4df1fe317f3056a |
completed | April 1, 2026, 12:01 a.m. |
| PD | Predicate disambiguation | batch_69cc5c23d08481908d8c9b0ad3d1dc00 |
completed | March 31, 2026, 11:43 p.m. |
Created at: March 30, 2026, 6:47 p.m.