Triple
T30319912
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Siege of Perusia |
E771170
|
entity |
| Predicate | outcomeForCity |
P37593
|
FINISHED |
| Object | Perusia captured by Octavian |
—
|
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: Perusia captured by Octavian | Statement: [Siege of Perusia, outcomeForCity, Perusia captured by Octavian]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: outcomeForCity Context triple: [Siege of Perusia, outcomeForCity, Perusia captured by Octavian]
-
A.
cityOutcome
chosen
Indicates the result, status, or consequence associated with a particular city in a given context.
-
B.
outcomeOf
Indicates that one entity is the result, consequence, or product that arises from another entity, event, or process.
-
C.
finalCity
Indicates that a given city is the last or ultimate city associated with an entity within a sequence, process, or journey.
-
D.
urbanPlanningOutcome
Indicates the result or impact that urban planning decisions or processes have on a place, system, or population.
-
E.
governsOutcome
Indicates that one entity has decisive control or influence over the result or consequence affecting 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_69f22489ee8481909344649bfbb92e83 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6abaa1f648190b77073771df3bf3b |
completed | May 3, 2026, 1:58 a.m. |
| PD | Predicate disambiguation | batch_69f6aa1e84b88190b025f6ca40f17a8a |
completed | May 3, 2026, 1:51 a.m. |
Created at: April 29, 2026, 7:52 p.m.