Triple
T27959451
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | House of Cao |
E704538
|
entity |
| Predicate | lastEmperorReignTitle |
P102119
|
FINISHED |
| Object | Emperor Yuan of Wei |
—
|
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: Emperor Yuan of Wei | Statement: [House of Cao, lastEmperorReignTitle, Emperor Yuan of Wei]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lastEmperorReignTitle Context triple: [House of Cao, lastEmperorReignTitle, Emperor Yuan of Wei]
-
A.
lastEmperorTitle
chosen
Indicates that the associated title is the final imperial title held by the last reigning emperor of a given realm or dynasty.
-
B.
emperorTitle
Indicates that one entity holds the title or rank of emperor in relation to another entity.
-
C.
reigningEmperorPersonalName
Indicates the personal name of the individual who is currently serving as the reigning emperor.
-
D.
emperorTitleContext
Indicates the contextual circumstances or domain (such as time, region, or political system) in which an individual holds or is referred to by an emperor title.
-
E.
titleBeforeEmperor
Indicates that one entity held a particular title or rank prior to becoming emperor.
- 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_69ef841061e48190b5570f9562f7434d |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_69f63b0218808190b3e543cc1a0bb5cb |
completed | May 2, 2026, 5:57 p.m. |
| PD | Predicate disambiguation | batch_69f63710d17c819084cfe96e6df334fd |
completed | May 2, 2026, 5:40 p.m. |
Created at: April 27, 2026, 7:30 p.m.