Triple
T31077440
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Basilica Porcia |
E792002
|
entity |
| Predicate | officeHeldByBuilder |
P45587
|
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: [Basilica Porcia, officeHeldByBuilder, censor of Rome]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeHeldByBuilder Context triple: [Basilica Porcia, officeHeldByBuilder, censor of Rome]
-
A.
officeHeldByDesigner
Indicates that a particular office or official position is occupied or held by a given designer.
-
B.
officeHeldByImplementer
Indicates that a particular office or position is held by the implementer (the entity responsible for carrying out a plan, project, or action).
-
C.
officeHeldByActor
Indicates that a specific office, position, or role is held or occupied by a particular actor.
-
D.
officeHeldOf
chosen
Indicates that a specific office or position is (or was) held by a particular person or entity.
-
E.
officeHeldTogetherWith
Indicates that two or more individuals simultaneously held the same office or position during an overlapping period.
- 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_69f224ccdbbc81909b0cdb4cc2d70c7a |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69feb5e66224819083b87c3707a5a5e0 |
completed | May 9, 2026, 4:19 a.m. |
| PD | Predicate disambiguation | batch_69feb3bd700c8190991ed200cd3c04db |
completed | May 9, 2026, 4:10 a.m. |
Created at: April 29, 2026, 9:02 p.m.