Triple
T32591810
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lucy Diamond Dawson |
E833090
|
entity |
| Predicate | hasParentWithDisability |
P198942
|
FINISHED |
| Object | Sam Dawson |
—
|
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: Sam Dawson | Statement: [Lucy Diamond Dawson, hasParentWithDisability, Sam Dawson]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasParentWithDisability Context triple: [Lucy Diamond Dawson, hasParentWithDisability, Sam Dawson]
-
A.
hasChildInCare
Indicates that one entity has responsibility for caring for another entity in a child or dependent role.
-
B.
hasParentalUnit
Indicates that an entity has a parent or guardian that serves as its primary caregiving or parental figure.
-
C.
hasChildWithAutism
Indicates that one entity has a child who has been diagnosed with autism.
-
D.
hasParentAuthority
Indicates that one entity holds a higher-level or supervisory authority over another, similar to a parent organization’s control over a subordinate.
-
E.
hasDisabilityRepresentation
Indicates that something includes, portrays, or accounts for the presence and experiences of people with disabilities.
- 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_69f34929ff648190aded9424aa7564ae |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69ff16775a9881909d26dbc1f0ef3e1c |
completed | May 9, 2026, 11:11 a.m. |
| PD | Predicate disambiguation | batch_69ff158e61708190a1c581d0d306cfce |
completed | May 9, 2026, 11:07 a.m. |
| PDg | Predicate description generation | batch_69ff167608f08190b7cd2cf65ddecbf3 |
completed | May 9, 2026, 11:11 a.m. |
Created at: May 1, 2026, 1:05 a.m.