Triple
T1322127
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alonso Pérez de Guzmán, 7th Duke of Medina Sidonia |
E28241
|
entity |
| Predicate | ordinalInTitle |
P18767
|
FINISHED |
| Object | 7 |
—
|
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: 7 | Statement: [Alonso Pérez de Guzmán, 7th Duke of Medina Sidonia, ordinalInTitle, 7]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ordinalInTitle Context triple: [Alonso Pérez de Guzmán, 7th Duke of Medina Sidonia, ordinalInTitle, 7]
-
A.
ordinalNumber
Indicates the position or rank of an entity within an ordered sequence (e.g., first, second, third).
-
B.
ordinalInOffice
Indicates the numerical order or rank of an individual’s term or tenure in a particular office or position.
-
C.
higherTitleOf
Indicates that one entity holds a job or position title that is hierarchically superior to the title held by another entity.
-
D.
nobleTitleNumber
chosen
Indicates the ordinal number or sequence position associated with a person's noble title (e.g., first duke, second baron).
-
E.
titleNumber
Indicates the numerical designation or sequence number assigned to a title within an ordered set of titles.
- 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_69a498540a2481909e807a762280d3ba |
completed | March 1, 2026, 7:49 p.m. |
| NER | Named-entity recognition | batch_69a4c19b76b48190aa8857b80971a842 |
completed | March 1, 2026, 10:45 p.m. |
| PD | Predicate disambiguation | batch_69a4beedb49c8190beb5b85cdda05013 |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:55 p.m.