Triple
T36433613
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Siege of Zaragoza (778) |
E897508
|
entity |
| Predicate | outcomeForDefenders |
P6933
|
FINISHED |
| Object | successful resistance against siege |
—
|
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: successful resistance against siege | Statement: [Siege of Zaragoza (778), outcomeForDefenders, successful resistance against siege]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: outcomeForDefenders Context triple: [Siege of Zaragoza (778), outcomeForDefenders, successful resistance against siege]
-
A.
awardedToDefenders
Indicates that something (such as a title, honor, or recognition) is granted specifically to entities serving in a defensive role.
-
B.
objectiveOfDefenders
Indicates that a particular goal, task, or purpose is assigned to or pursued by the defenders in a given context.
-
C.
defenderIn
Indicates that an entity serves as a defensive agent or protector within a specified context, situation, or domain.
-
D.
defenseResult
chosen
Indicates the outcome or consequence of a defensive action or strategy in response to an attack or threat.
-
E.
defender
Indicates a relationship where one entity protects, guards, or supports another entity against threats, attacks, or criticism.
- 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_69f76e56636481908eda808ab0273401 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7c777e924819081a6634f549fe552 |
completed | May 3, 2026, 10:08 p.m. |
| PD | Predicate disambiguation | batch_69f7c477a4d481908f52e55b6688f60c |
completed | May 3, 2026, 9:56 p.m. |
Created at: May 3, 2026, 4:10 p.m.