Triple
T25988769
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Decretal to Himerius of Tarragona |
E646279
|
entity |
| Predicate | mentionsOffice |
P158813
|
FINISHED |
| Object | bishops |
—
|
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: bishops | Statement: [Decretal to Himerius of Tarragona, mentionsOffice, bishops]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mentionsOffice Context triple: [Decretal to Himerius of Tarragona, mentionsOffice, bishops]
-
A.
mentionsOffice
chosen
Indicates that one entity explicitly refers to or brings up an office (such as a workplace, office location, or office role) in relation to another entity.
-
B.
officeIs
Indicates that one entity serves as the office or official workplace location of another entity.
-
C.
officeIn
Indicates that one entity has an office located within the premises or jurisdiction of another entity.
-
D.
includedOffice
Indicates that one office is contained within, or forms part of, another office or organizational unit.
-
E.
worksWithOffice
Indicates that an entity collaborates or is professionally associated with a particular office or office-based organization.
- 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_69e77e881fc08190ba1c8dc7e2a07f97 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f605469f7881909fb9d981d79def18 |
completed | May 2, 2026, 2:08 p.m. |
| PD | Predicate disambiguation | batch_69f4a10480748190a2e67bd399fc435d |
completed | May 1, 2026, 12:48 p.m. |
Created at: April 22, 2026, 8:55 a.m.