Triple
T28829121
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jiefangbei area |
E727993
|
entity |
| Predicate | hasCenterpiece |
P70902
|
FINISHED |
| Object | Jiefangbei Liberation Monument |
—
|
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: Jiefangbei Liberation Monument | Statement: [Jiefangbei area, hasCenterpiece, Jiefangbei Liberation Monument]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCenterpiece Context triple: [Jiefangbei area, hasCenterpiece, Jiefangbei Liberation Monument]
-
A.
heightOfCenterpiece
Indicates the measured vertical height of the centerpiece in the given context or arrangement.
-
B.
hasCrowningJewel
Indicates that one entity possesses or is characterized by a most important, standout, or premier element represented by another entity.
-
C.
hasCentralFigure
Indicates that something features a primary or most important figure at its core or focus.
-
D.
visualCenterpiece
chosen
Indicates that one entity serves as the primary visual focus or dominant visual element in relation to another entity.
-
E.
hasCentralStoneType
Indicates that an item, typically a piece of jewelry, features a central stone of a specified type.
- 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_69f0319dc6088190bbfaa206d40ed74a |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f6d0d46aec819091edf97324d793ac |
completed | May 3, 2026, 4:36 a.m. |
| PD | Predicate disambiguation | batch_69f6cfe2183481908ae4e85a59c66f69 |
completed | May 3, 2026, 4:32 a.m. |
Created at: April 28, 2026, 6:37 a.m.