Triple
T33302209
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ostroh Castle |
E852614
|
entity |
| Predicate | historicallyInState |
P135339
|
FINISHED |
| Object | Grand Duchy of Lithuania |
—
|
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: Grand Duchy of Lithuania | Statement: [Ostroh Castle, historicallyInState, Grand Duchy of Lithuania]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: historicallyInState Context triple: [Ostroh Castle, historicallyInState, Grand Duchy of Lithuania]
-
A.
historicalState
Indicates that an entity existed in a particular state or condition during a specified time in the past.
-
B.
historicalStatusOf
Indicates the historical condition, role, or classification that an entity held during a specific past period or context.
-
C.
governingStateInHistory
chosen
Indicates that one state historically exercised governing authority or control over another entity during a specific period in the past.
-
D.
historicState
Indicates that an entity was formerly a state or political entity in the past but no longer holds that status in the present.
-
E.
historicallyIn
Indicates that one entity existed, occurred, or was situated within the historical context, period, or jurisdiction associated with another entity.
- 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_69f34966ed4c81908dc9dda82d8c7fe3 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fff09dae088190bd8460060d778feb |
completed | May 10, 2026, 2:42 a.m. |
| PD | Predicate disambiguation | batch_69fff0027c5c8190baa5c7a15852cbe0 |
completed | May 10, 2026, 2:40 a.m. |
Created at: May 1, 2026, 1:33 a.m.