Triple
T27498290
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rayleigh family |
E694075
|
entity |
| Predicate | hasNobleTitleCreatedIn |
P190951
|
FINISHED |
| Object | Peerage of the United Kingdom |
—
|
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: Peerage of the United Kingdom | Statement: [Rayleigh family, hasNobleTitleCreatedIn, Peerage of the United Kingdom]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNobleTitleCreatedIn Context triple: [Rayleigh family, hasNobleTitleCreatedIn, Peerage of the United Kingdom]
-
A.
nobleTitleCreatedIn
chosen
Indicates that a specific noble title was formally established or instituted in a particular place or jurisdiction.
-
B.
hasNobleStatus
Indicates that an entity possesses a recognized noble rank, title, or aristocratic status.
-
C.
hasNoble
Indicates that one entity possesses or is associated with a noble title, status, or noble individual.
-
D.
hasNobleTitleCount
Indicates the number of noble titles that are associated with or held by a given entity.
-
E.
nobleTitleCreationDate
Indicates the date on which a particular noble title was formally created or granted.
- 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_69ef538370888190b1ddf53bb4831188 |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69fe91383a1c81909266e40c3c3ede6c |
completed | May 9, 2026, 1:43 a.m. |
| PD | Predicate disambiguation | batch_69fe8fde094081908f0f121664fbb5c7 |
completed | May 9, 2026, 1:37 a.m. |
Created at: April 27, 2026, 1:09 p.m.