Triple
T27330695
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harold Wilkinson |
E689789
|
entity |
| Predicate | notableRelativeRoleOfSibling |
P123178
|
FINISHED |
| Object | British Labour politician |
—
|
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: British Labour politician | Statement: [Harold Wilkinson, notableRelativeRoleOfSibling, British Labour politician]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableRelativeRoleOfSibling Context triple: [Harold Wilkinson, notableRelativeRoleOfSibling, British Labour politician]
-
A.
siblingNotableFor
Indicates that a sibling of the subject is recognized or distinguished for a particular achievement, role, or characteristic.
-
B.
siblingOrRelative
Indicates that two entities are related to each other by blood, marriage, or family ties, including but not limited to being siblings.
-
C.
notableRelative
Indicates that an entity has a relative who is notable or well-known, specifying that familial relationship.
-
D.
notableRelativeType
chosen
Indicates the specific familial or relational role that a notable relative has in relation to the subject.
-
E.
sibling
Indicates that two entities share at least one parent, making them brothers or sisters to each other.
- 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_69ef355d4cb08190ab032c0a2e7d3753 |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69ffb97b8ff8819088b105d99a0820c9 |
completed | May 9, 2026, 10:47 p.m. |
| PD | Predicate disambiguation | batch_69ffb88ef7388190a710120ed76edc0e |
completed | May 9, 2026, 10:43 p.m. |
Created at: April 27, 2026, 11:38 a.m.