Triple
T29917517
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 中元節 |
E759825
|
entity |
| Predicate | 時間特徵 |
P42651
|
FINISHED |
| Object | 鬼門開期間的重要日子 |
—
|
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: 鬼門開期間的重要日子 | Statement: [中元節, 時間特徵, 鬼門開期間的重要日子]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 時間特徵 Context triple: [中元節, 時間特徵, 鬼門開期間的重要日子]
-
A.
timeCharacteristic
chosen
Indicates a relationship where one entity specifies a temporal property, feature, or constraint that characterizes another entity or event.
-
B.
tempoFeature
Indicates a relationship where a musical or rhythmic element is characterized by, or associated with, a specific tempo-related property or feature.
-
C.
timeIndexed
Indicates that the relationship or property it connects is associated with, or valid during, a specific time or time interval.
-
D.
timePeriod
Indicates the specific span or interval of time during which an event, state, or relationship occurs or is valid.
-
E.
timeCoordinate
Indicates a relationship where a specific time value is used to locate or reference an event, state, or object along a temporal axis or timeline.
- 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_69f2246189fc8190996b63ee1f9a2374 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f677907930819081cd718537fdaf4a |
completed | May 2, 2026, 10:15 p.m. |
| PD | Predicate disambiguation | batch_69f66ec8298c8190b41fe9d182c05676 |
completed | May 2, 2026, 9:38 p.m. |
Created at: April 29, 2026, 6:13 p.m.