Triple
T28187583
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zhongshu Sheng |
E716218
|
entity |
| Predicate | servedRulerType |
P27868
|
FINISHED |
| Object | emperor of China |
—
|
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: emperor of China | Statement: [Zhongshu Sheng, servedRulerType, emperor of China]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servedRulerType Context triple: [Zhongshu Sheng, servedRulerType, emperor of China]
-
A.
providedRulerFor
Indicates that one entity supplied or designated another entity to serve as the ruler or governing authority over a particular domain or group.
-
B.
recognizedAsRuler
Indicates that one entity is acknowledged or accepted by others as the legitimate ruler or sovereign authority.
-
C.
hasTypeOfRuler
chosen
Indicates that one entity serves as the specific kind or category of ruler (e.g., monarch, dictator, president) that characterizes or governs another entity.
-
D.
rulerSpecies
Indicates that a particular species serves as the ruling or dominant governing group over another entity or domain.
-
E.
targetedRuler
Indicates that an entity intentionally directed hostile or coercive actions specifically against a ruling individual or authority figure.
- 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_69efd6b612f48190a72012b520afbd10 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69fd4d1854988190be093b103a681798 |
completed | May 8, 2026, 2:40 a.m. |
| PD | Predicate disambiguation | batch_69fd4c8d1a188190897c24527337814a |
completed | May 8, 2026, 2:38 a.m. |
Created at: April 27, 2026, 10:23 p.m.