Triple
T33047616
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tocco of Epirus |
E845636
|
entity |
| Predicate | ruledCities |
P46958
|
FINISHED |
| Object | Ioannina |
—
|
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: Ioannina | Statement: [Tocco of Epirus, ruledCities, Ioannina]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ruledCities Context triple: [Tocco of Epirus, ruledCities, Ioannina]
-
A.
ruledCity
chosen
Indicates that a person or governing entity exercised political authority or control over a specific city.
-
B.
cityOwned
Indicates that something is owned, managed, or under the jurisdiction of a city or municipal government.
-
C.
hasNumberOfImperialCities
Indicates the relationship between an entity and the count of imperial cities associated with or contained within it.
-
D.
realmRuled
Indicates that one entity serves as the sovereign or governing ruler over a particular realm, territory, or domain.
-
E.
alsoRuled
Indicates that two or more entities shared ruling authority over the same domain or subjects, either concurrently or at different times.
- 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_69f3495242e48190996a2cb2beab5455 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6d6a6b04c8190bee4cf9c00665ef7 |
completed | May 3, 2026, 5:01 a.m. |
| PD | Predicate disambiguation | batch_69f6d27120988190aacec621cf2bf0e8 |
completed | May 3, 2026, 4:43 a.m. |
Created at: May 1, 2026, 1:24 a.m.