Triple
T33929809
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duchy of Oleśnica |
E869856
|
entity |
| Predicate | dynastyRuling |
P47786
|
FINISHED |
| Object | Piast 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: Piast dynasty | Statement: [Duchy of Oleśnica, dynastyRuling, Piast dynasty]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dynastyRuling Context triple: [Duchy of Oleśnica, dynastyRuling, Piast dynasty]
-
A.
dynastyRuled
chosen
Indicates that a particular dynasty held ruling authority or governance over a specified region, state, or people during a certain period.
-
B.
reignInDynasty
Indicates that a person’s reign or rule occurs within the context of a specific dynasty.
-
C.
dynastyServed
Indicates that a person or group rendered service or allegiance to a particular ruling dynasty.
-
D.
associatedDynastyRuler
Indicates a relationship where a dynasty is linked to the ruler who governed or is historically connected with it.
-
E.
producedRulingDynastyOf
Indicates that one entity (such as a region, people, or prior polity) gave rise to or was the origin context for a particular ruling dynasty.
- 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_69f3499a59788190bff762a891471b31 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7064e906881909c3186c646145d34 |
completed | May 3, 2026, 8:24 a.m. |
| PD | Predicate disambiguation | batch_69f70100ec1c8190a6b97f50e88891f2 |
completed | May 3, 2026, 8:02 a.m. |
Created at: May 1, 2026, 1:49 a.m.