Triple
T38701159
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Lyttelton, 11th Viscount Cobham |
E950141
|
entity |
| Predicate | ordinal of title |
P80266
|
FINISHED |
| Object | 11th Viscount Cobham |
—
|
NE NERFINISHED |
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: 11th Viscount Cobham | Statement: [John Lyttelton, 11th Viscount Cobham, ordinal of title, 11th Viscount Cobham]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ordinal of title Context triple: [John Lyttelton, 11th Viscount Cobham, ordinal of title, 11th Viscount Cobham]
-
A.
ordinalInFamilyTitle
chosen
Indicates that a title or role specifies an entity’s numerical position within a family sequence (e.g., first, second, third).
-
B.
higherTitleOf
Indicates that one entity holds a job or position title that is hierarchically superior to the title held by another entity.
-
C.
aristocraticTitleOrder
Indicates the hierarchical ranking or precedence relationship between different aristocratic titles.
-
D.
hasOrdinaryTitle
Indicates that an entity holds a standard, non-noble or non-honorific title associated with its role or position.
-
E.
titleHierarchy
Indicates a hierarchical relationship between titles, where one title is ranked above or below another in an ordered structure.
- 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_69f76f0124408190bb39c3040734846b |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fce545fec881909247a3af821d21ae |
completed | May 7, 2026, 7:17 p.m. |
| PD | Predicate disambiguation | batch_69fce12eaeec81908cf81346b2cef6e0 |
completed | May 7, 2026, 6:59 p.m. |
Created at: May 3, 2026, 4:33 p.m.