Triple
T26630611
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Skandar Keynes |
E668478
|
entity |
| Predicate | ancestralFamily |
P101267
|
FINISHED |
| Object | Darwin–Wedgwood family |
—
|
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: Darwin–Wedgwood family | Statement: [Skandar Keynes, ancestralFamily, Darwin–Wedgwood family]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ancestralFamily Context triple: [Skandar Keynes, ancestralFamily, Darwin–Wedgwood family]
-
A.
ancestralGroup
Indicates that one entity is a broader ancestral lineage, population, or group from which the other entity descends or originates.
-
B.
ancestorHouse
Indicates that one entity is the house or dwelling associated with the ancestors of another entity.
-
C.
ancestralLinks
chosen
Indicates a genealogical relationship where one entity is an ancestor of, or connected through a line of descent to, another entity.
-
D.
historicalFamily
Indicates a familial relationship that existed between entities in the past, regardless of whether it still holds in the present.
-
E.
ancestralStatus
Indicates that one entity holds a particular ancestral or lineage-based relationship or status in relation to another entity.
- 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_69ee9cff507c819092b95bf7219a702e |
completed | April 26, 2026, 11:17 p.m. |
| NER | Named-entity recognition | batch_69f61a17a7788190946f7e32d63cd43f |
completed | May 2, 2026, 3:36 p.m. |
| PD | Predicate disambiguation | batch_69f611ab768c8190b1849c15a3e59dda |
completed | May 2, 2026, 3 p.m. |
Created at: April 27, 2026, 2:25 a.m.