Triple
T33565384
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duke of Lerma |
E859743
|
entity |
| Predicate | politicalRoleOfFamousHolder |
P131089
|
FINISHED |
| Object | royal favorite |
—
|
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: royal favorite | Statement: [Duke of Lerma, politicalRoleOfFamousHolder, royal favorite]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: politicalRoleOfFamousHolder Context triple: [Duke of Lerma, politicalRoleOfFamousHolder, royal favorite]
-
A.
officeHolderOccupation
Indicates that the occupation describes the role or job held by an office holder.
-
B.
officeHoldersHaveRole
chosen
Indicates that individuals or entities holding an office possess or are assigned a specific role associated with that office.
-
C.
notableFormerHolderRole
Indicates that an entity previously held a particular notable role or position.
-
D.
officeHolderRoleFor
Indicates that a specific role or position is held by an office holder within an organization or governing body.
-
E.
officeHolderOf
Indicates that a person holds or has held an official position or role within a specified organization, institution, or 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_69f3497c1d288190a844ea699914e038 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fe59d11e9881909d2f33b7c717030e |
completed | May 8, 2026, 9:46 p.m. |
| PD | Predicate disambiguation | batch_69fe394fdfbc8190a931926ae3635cbf |
completed | May 8, 2026, 7:28 p.m. |
Created at: May 1, 2026, 1:40 a.m.