Triple
T1449698
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marquess of Blandford |
E31260
|
entity |
| Predicate | titleHolderIsUsually |
P28721
|
FINISHED |
| Object | eldest son of the Duke of Marlborough |
—
|
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: eldest son of the Duke of Marlborough | Statement: [Marquess of Blandford, titleHolderIsUsually, eldest son of the Duke of Marlborough]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: titleHolderIsUsually Context triple: [Marquess of Blandford, titleHolderIsUsually, eldest son of the Duke of Marlborough]
-
A.
titleHolderType
Indicates the specific role or capacity in which an entity holds a title (e.g., owner, trustee, beneficiary).
-
B.
titleHolderSince
Indicates the entity that has held a particular title or position continuously from a specified starting time.
-
C.
titleHolderMother
Indicates that the subject is the mother of the current or specified holder of a particular title.
-
D.
titleHolderFullName
Indicates the full personal name of the entity that holds a particular title or position.
-
E.
titleHolderClass
Indicates the class or category of entity that holds or bears a particular title.
- F. None of above. chosen
Provenance (4 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_69a499171a28819085b993a3ac78e363 |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c55d923c8190957756f834f94462 |
completed | March 1, 2026, 11:01 p.m. |
| PD | Predicate disambiguation | batch_69a4c47a840c819083307a65c027a19e |
completed | March 1, 2026, 10:58 p.m. |
| PDg | Predicate description generation | batch_69a4c55508948190922aee3230a4323e |
completed | March 1, 2026, 11:01 p.m. |
Created at: March 1, 2026, 8 p.m.