Triple
T28724572
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Empress Xiaoming |
E730185
|
entity |
| Predicate | empressOf |
P121116
|
FINISHED |
| Object | Song dynasty |
—
|
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: Song dynasty | Statement: [Empress Xiaoming, empressOf, Song dynasty]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: empressOf Context triple: [Empress Xiaoming, empressOf, Song dynasty]
-
A.
eraAsEmpress
Indicates the time period during which a person held the role or status of empress.
-
B.
realmAsEmpress
chosen
Indicates that an entity holds the position or role of empress over a specified realm or domain.
-
C.
reignAsEmpress
Indicates that a person holds and exercises the supreme imperial authority in the role of empress over a realm or empire.
-
D.
associatedEmpress
Indicates a relationship where an empress is linked or connected to another entity, such as a person, place, event, or object, in a relevant or context-specific way.
-
E.
producedEmpress
Indicates that one entity created, generated, or brought about the existence or status of an empress.
- 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_69f043e91fe48190b73bcd8e08d433e0 |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69f6570caa888190b05d9aa932648185 |
completed | May 2, 2026, 7:57 p.m. |
| PD | Predicate disambiguation | batch_69f651ac855481908e30c3b345d31356 |
completed | May 2, 2026, 7:34 p.m. |
Created at: April 28, 2026, 5:55 a.m.