Triple
T31428456
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman military institutions |
E801729
|
entity |
| Predicate | hasCommandOffice |
P147320
|
FINISHED |
| Object | consul |
—
|
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: consul | Statement: [Roman military institutions, hasCommandOffice, consul]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCommandOffice Context triple: [Roman military institutions, hasCommandOffice, consul]
-
A.
hasProperOffice
Indicates that an entity maintains an officially designated, appropriate office or place of business.
-
B.
hasOffice
Indicates that an entity possesses or maintains an office at a particular location or within a specific organization.
-
C.
hasSupportingOffice
Indicates that an entity is associated with or served by a particular office that provides support or administrative services to it.
-
D.
hasAssociatedOffice
Indicates that an entity is linked to or connected with a particular office in an official or functional capacity.
-
E.
overseesOffice
chosen
Indicates that one entity has managerial or supervisory responsibility for the operations or activities of a particular office.
- 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_69f348c475348190bf579ca858eec77c |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_6a0224f4b6cc8190a8f79700a9af765f |
completed | May 11, 2026, 6:50 p.m. |
| PD | Predicate disambiguation | batch_6a0223f01eb081909419518fdd45f2a4 |
completed | May 11, 2026, 6:46 p.m. |
Created at: April 30, 2026, 8:55 p.m.