Triple
T31283363
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vendôme Column |
E797734
|
entity |
| Predicate | originalStatue |
P104222
|
FINISHED |
| Object | statue of Napoleon in Roman attire |
—
|
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: statue of Napoleon in Roman attire | Statement: [Vendôme Column, originalStatue, statue of Napoleon in Roman attire]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalStatue Context triple: [Vendôme Column, originalStatue, statue of Napoleon in Roman attire]
-
A.
statueSubject
Indicates that one entity is the subject or theme represented by a statue of another entity.
-
B.
topStatue
chosen
Indicates that one entity is positioned as a statue on top of another entity.
-
C.
statueName
Indicates that a statue has a specific name or title associated with it.
-
D.
hasStatueOrigin
Indicates that a statue was created in, derived from, or originally located in a specified place or source.
-
E.
previousRoofStatue
Indicates that one entity served as the earlier or former roof statue relative to another entity.
- 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_69f224def9088190a37034eab3daf57f |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_6a00a15604fc8190b1c280794960f3a4 |
completed | May 10, 2026, 3:16 p.m. |
| PD | Predicate disambiguation | batch_6a00a0f7e77881909ac85755ab0e6329 |
completed | May 10, 2026, 3:15 p.m. |
Created at: April 29, 2026, 9:13 p.m.