Triple
T7449060
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duchess of Marlborough |
E171958
|
entity |
| Predicate | familySeatFunction |
P76981
|
FINISHED |
| Object | symbol of Marlborough family status |
—
|
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: symbol of Marlborough family status | Statement: [Duchess of Marlborough, familySeatFunction, symbol of Marlborough family status]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: familySeatFunction Context triple: [Duchess of Marlborough, familySeatFunction, symbol of Marlborough family status]
-
A.
familySeat
Indicates the traditional principal residence or ancestral home associated with a particular family or lineage.
-
B.
familySeatGiftedBy
Indicates that a family seat (such as an estate or ancestral property) was granted or given to someone by a specified donor.
-
C.
familySeatGiftedFor
Indicates that a family’s hereditary seat or estate was granted or bestowed to a recipient, rather than acquired by inheritance or purchase.
-
D.
familySeatRegion
Indicates the region in which a family's principal seat, base, or ancestral home is located.
-
E.
familyRide
Indicates that one entity participates in a ride or journey together with their family members.
- 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_69c68a65402881908f7869368eb746fb |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f389ddd48190a4b8753c67220c4f |
completed | March 27, 2026, 9:15 p.m. |
| PD | Predicate disambiguation | batch_69c6f039f7248190bb4183f97b605763 |
completed | March 27, 2026, 9:01 p.m. |
| PDg | Predicate description generation | batch_69c6f1ee5ab8819091082324f2dc3b8c |
completed | March 27, 2026, 9:09 p.m. |
Created at: March 27, 2026, 3:14 p.m.