Triple
T19062877
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Baron Darling of Roulanish |
E466579
|
entity |
| Predicate | granteePosition |
P97735
|
FINISHED |
| Object | former Chancellor of the Exchequer |
—
|
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: former Chancellor of the Exchequer | Statement: [Baron Darling of Roulanish, granteePosition, former Chancellor of the Exchequer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: granteePosition Context triple: [Baron Darling of Roulanish, granteePosition, former Chancellor of the Exchequer]
-
A.
granteeFullName
Indicates the complete personal name of the entity that receives a grant or is designated as the grantee.
-
B.
ownerPosition
Indicates the spatial or positional relationship of an owner relative to the owned entity.
-
C.
grantedAs
chosen
Indicates that one entity is conferred, assigned, or bestowed in a particular role, status, or capacity to another entity.
-
D.
grantedBy
Indicates that a right, permission, or benefit is conferred or authorized by one entity to another.
-
E.
grantRecipient
Indicates that one entity is the recipient or beneficiary of a grant provided by another entity.
- 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_69d8dd040fb881909af2a964f65ad208 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e195ac048190a57b57e585d022d4 |
completed | April 20, 2026, 8:19 a.m. |
| PD | Predicate disambiguation | batch_69e4b99633c8819097988608c278ecf8 |
completed | April 19, 2026, 11:16 a.m. |
Created at: April 10, 2026, 12:03 p.m.