Triple
T29742411
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gaius Marius the Younger |
E752646
|
entity |
| Predicate | besiegedAt |
P36192
|
FINISHED |
| Object | Praeneste |
—
|
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: Praeneste | Statement: [Gaius Marius the Younger, besiegedAt, Praeneste]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: besiegedAt Context triple: [Gaius Marius the Younger, besiegedAt, Praeneste]
-
A.
wasBesiegedBy
Indicates that an entity (typically a place or stronghold) was subjected to a military siege carried out by another entity.
-
B.
siegeOccurredIn
Indicates that a siege took place within or at the location specified by the related entity.
-
C.
besiegedIn
chosen
Indicates that one entity is under siege at, or during the event of, another specified location or time.
-
D.
sieged
Indicates that one entity has surrounded and blockaded another entity or location, typically to cut off supplies and force surrender.
-
E.
fortificationTypeAssaulted
Indicates that an assault or attack was carried out against a specific type of fortification.
- 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_69f0d62b064081908c1ae61cd68fb139 |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f673645c888190bdffeb6448487ec4 |
completed | May 2, 2026, 9:57 p.m. |
| PD | Predicate disambiguation | batch_69f66ac1a4fc81909740d2e52fbe6970 |
completed | May 2, 2026, 9:21 p.m. |
Created at: April 28, 2026, 7:48 p.m.