Triple
T33047324
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Byzantine garrison of Nicomedia |
E845630
|
entity |
| Predicate | garrisonedCity |
P10998
|
FINISHED |
| Object | Nicomedia |
—
|
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: Nicomedia | Statement: [Byzantine garrison of Nicomedia, garrisonedCity, Nicomedia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: garrisonedCity Context triple: [Byzantine garrison of Nicomedia, garrisonedCity, Nicomedia]
-
A.
garrisonTown
chosen
Indicates that a town serves as a military base or station where armed forces are permanently or regularly housed.
-
B.
garrisonIncluded
Indicates that a particular garrison is included within, or forms part of, a specified larger military force, unit, or installation.
-
C.
surroundedCity
Indicates that one city is encircled or completely enclosed by another city or its surrounding territory.
-
D.
primaryDefendedCity
Indicates that an entity served as the main or principal city that another entity was responsible for defending.
-
E.
garrisonedDuring
Indicates that a military force was stationed or quartered at a location for defense or control during a specified time period.
- 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.