Triple
T17048666
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Civil Lord of the Admiralty |
E413636
|
entity |
| Predicate | officeHolderClassification |
P15556
|
FINISHED |
| Object | civil lord |
—
|
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: civil lord | Statement: [Civil Lord of the Admiralty, officeHolderClassification, civil lord]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeHolderClassification Context triple: [Civil Lord of the Admiralty, officeHolderClassification, civil lord]
-
A.
officeHolderClass
chosen
Indicates that a given role or position is held by members belonging to a specified class or category of office holders.
-
B.
officeHolderOf
Indicates that a person holds or has held an official position or role within a specified organization, institution, or office.
-
C.
officeHolderIs
Indicates that one entity serves as the office holder (e.g., official or position occupant) of another entity, such as an office, role, or institution.
-
D.
officeHolderRoleFor
Indicates that a specific role or position is held by an office holder within an organization or governing body.
-
E.
officeHolderTypicallyFrom
Indicates that the person holding a particular office is typically drawn from or originates from a specified group, region, or category.
- 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_69d886cd18288190b006abab23f811b7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3daa092f08190a9e37404a9de662c |
completed | April 18, 2026, 7:25 p.m. |
| PD | Predicate disambiguation | batch_69e35d60a588819084f53ef9f8b2e7c0 |
completed | April 18, 2026, 10:30 a.m. |
Created at: April 10, 2026, 5:34 a.m.