Triple
T8001082
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Centurion |
E186248
|
entity |
| Predicate | wasKeyElementOf |
P66826
|
FINISHED |
| Object | Roman military command structure |
—
|
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: Roman military command structure | Statement: [Centurion, wasKeyElementOf, Roman military command structure]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasKeyElementOf Context triple: [Centurion, wasKeyElementOf, Roman military command structure]
-
A.
wasIn
Indicates that an entity existed, occurred, or was located within a particular place or context during a specified time or situation.
-
B.
isKeyPartOf
chosen
Indicates that something functions as an essential component or crucial element within a larger whole.
-
C.
wereInternedBy
Indicates that an entity was forcibly confined, detained, or held in an internment facility by another entity (typically an authority or government).
-
D.
usedToBePartOf
Indicates that an entity was formerly a component or member of another entity but is no longer part of it.
-
E.
wasAmong
Indicates that an entity belonged to, was included in, or was part of a particular group, set, or collection.
- 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_69ca82aaaf24819084b94d18f699ba53 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3c9cd06081908b62bb41e228c321 |
completed | March 31, 2026, 3:16 a.m. |
| PD | Predicate disambiguation | batch_69cb0483d3b48190b250c7603d747bca |
completed | March 30, 2026, 11:17 p.m. |
Created at: March 30, 2026, 5:17 p.m.