Triple
T32382727
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Imperial Palace |
E827464
|
entity |
| Predicate | rebuiltPeriod |
P151213
|
FINISHED |
| Object | post-1945 |
—
|
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: post-1945 | Statement: [Imperial Palace, rebuiltPeriod, post-1945]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rebuiltPeriod Context triple: [Imperial Palace, rebuiltPeriod, post-1945]
-
A.
rebuiltBetween
Indicates that an entity was reconstructed or rebuilt during a time interval bounded by two specified temporal points.
-
B.
rebuiltOn
Indicates that one entity has been reconstructed, restored, or built again on, over, or using the foundation, structure, or basis of another entity.
-
C.
rebuiltApproximateEndYear
chosen
Indicates that an entity was rebuilt, with the specified year representing an approximate (not exact) end date of the rebuilding process.
-
D.
rebuiltEvery
Indicates that one entity is reconstructed or built anew at regular intervals defined by another entity.
-
E.
rebuiltCompletedIn
Indicates that an entity has undergone a rebuilding process that was fully completed in a specified time or event.
- 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_69f349177ddc8190ab0583f05597056b |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6c1ccf26c8190bb23c288a91cf08a |
completed | May 3, 2026, 3:32 a.m. |
| PD | Predicate disambiguation | batch_69f6ba6eb32c8190bf405b2011fa48f7 |
completed | May 3, 2026, 3:01 a.m. |
Created at: May 1, 2026, 12:51 a.m.