Triple
T30212003
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vas County (Kingdom of Hungary) |
E768091
|
entity |
| Predicate | governedByOfficial |
P98499
|
FINISHED |
| Object | ispán (comes) |
—
|
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: ispán (comes) | Statement: [Vas County (Kingdom of Hungary), governedByOfficial, ispán (comes)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: governedByOfficial Context triple: [Vas County (Kingdom of Hungary), governedByOfficial, ispán (comes)]
-
A.
areGovernedBy
chosen
Indicates that one or more entities are under the authority, control, or administration of a governing body or ruler.
-
B.
governedByAct
Indicates that something is regulated, controlled, or legally defined by a specific act or piece of legislation.
-
C.
governedByDeFacto
Indicates that an entity is effectively controlled or ruled in practice by another entity, regardless of formal or legal authority.
-
D.
governedFor
Indicates that one entity exercised governing authority or administrative control on behalf of, or in the interest of, another entity.
-
E.
governedIn
Indicates that one entity exercised governing authority or administrative control within a specified place or jurisdiction.
- 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_69f2247eb0848190b4032f302d39c0d9 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69ff691f5ae481908597ce245188d31c |
completed | May 9, 2026, 5:04 p.m. |
| PD | Predicate disambiguation | batch_69ff67ceeeb081909fd00cad166c4b6a |
completed | May 9, 2026, 4:58 p.m. |
Created at: April 29, 2026, 7:32 p.m.