Triple
T25646976
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Šibenik |
E642989
|
entity |
| Predicate | defendedEntity |
P6876
|
FINISHED |
| Object | city of Šibenik |
—
|
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: city of Šibenik | Statement: [Battle of Šibenik, defendedEntity, city of Šibenik]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: defendedEntity Context triple: [Battle of Šibenik, defendedEntity, city of Šibenik]
-
A.
defendedAs
Indicates that one entity is presented, argued, or justified as being equivalent to or serving the role of another entity in a defensive or protective context.
-
B.
defends
chosen
Indicates that one entity protects or supports another entity against attack, criticism, or harm.
-
C.
defendedOn
Indicates that one entity protected, supported, or argued in favor of another entity during a specific time or event.
-
D.
titleDefendedBy
Indicates that a specific title or championship is actively defended or held against challengers by a particular entity.
-
E.
isDefendedOn
Indicates that one entity provides protection, justification, or support for another entity in a specific context or situation.
- 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_69e77e7ce28081908b08d65ee6e5c8be |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f6352fdb788190b9bad30243690743 |
completed | May 2, 2026, 5:32 p.m. |
| PD | Predicate disambiguation | batch_69f63182f1408190bddc1214fcbd6145 |
completed | May 2, 2026, 5:16 p.m. |
Created at: April 21, 2026, 5:55 p.m.