Triple
T10018321
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Herculius |
E199551
|
entity |
| Predicate | usedByOfficeHolder |
P91722
|
FINISHED |
| Object | Roman emperor |
—
|
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 emperor | Statement: [Herculius, usedByOfficeHolder, Roman emperor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedByOfficeHolder Context triple: [Herculius, usedByOfficeHolder, Roman emperor]
-
A.
givenByOfficeHolder
Indicates that something (such as an award, decision, or document) is conferred or issued by a person acting in their capacity as an office holder.
-
B.
refersToOfficeHolder
Indicates that one entity is being used to denote, mention, or point specifically to a person who holds a particular office or official position.
-
C.
appliesToOfficeholder
Indicates that something (such as a rule, benefit, restriction, or obligation) is applicable specifically to a person holding a particular office or official position.
-
D.
involvesOfficeHolder
Indicates that the relationship or action includes or pertains to a person currently holding a specific office or official position.
-
E.
memberHoldsOffice
Indicates that a member occupies or serves in a specific official position or office within an organization or governing body.
- 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_69ca8315a1a08190ab310f25620f362b |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cdcd4de1588190a89ed575cff0b8c9 |
completed | April 2, 2026, 1:58 a.m. |
| PD | Predicate disambiguation | batch_69cd4b7cd4208190b2253583ee2f892c |
completed | April 1, 2026, 4:44 p.m. |
| PDg | Predicate description generation | batch_69cd4f8d9b888190b8067bd916dae773 |
completed | April 1, 2026, 5:02 p.m. |
Created at: March 30, 2026, 8:53 p.m.