Triple
T29438981
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Appian Aqueduct |
E746658
|
entity |
| Predicate | positionHeldByCommissioner |
P194805
|
FINISHED |
| Object | censor of Rome |
—
|
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: censor of Rome | Statement: [Appian Aqueduct, positionHeldByCommissioner, censor of Rome]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionHeldByCommissioner Context triple: [Appian Aqueduct, positionHeldByCommissioner, censor of Rome]
-
A.
positionHeld
Indicates that an entity occupies or has occupied a specific role, job, office, or position within an organization or context.
-
B.
positionHeldUnder
Indicates that one entity holds or held a specific position, office, or role under the authority, administration, or jurisdiction of another entity.
-
C.
positionHeldInJurisdiction
Indicates that an entity holds or has held a specific position, office, or role within a particular legal or geographic jurisdiction.
-
D.
appointedCommissioner
Indicates that one entity formally selected and assigned another entity to serve in the role of commissioner.
-
E.
coCommissioner
Indicates that two or more entities share joint responsibility and authority in commissioning something together.
- F. None of above. chosen
Provenance (4 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_69f0a7a180e48190ae775e40047dbcb5 |
completed | April 28, 2026, 12:27 p.m. |
| NER | Named-entity recognition | batch_69fd884cb2b48190b6acd473430d9e19 |
completed | May 8, 2026, 6:53 a.m. |
| PD | Predicate disambiguation | batch_69fd8709ca208190a8bab836f0156af5 |
completed | May 8, 2026, 6:47 a.m. |
| PDg | Predicate description generation | batch_69fd884b9d908190833de9500ff6d62a |
completed | May 8, 2026, 6:52 a.m. |
Created at: April 28, 2026, 3:19 p.m.