Triple
T37280456
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marcia Roy |
E925370
|
entity |
| Predicate | wealthStatusInStory |
P95466
|
FINISHED |
| Object | billionaire family member |
—
|
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: billionaire family member | Statement: [Marcia Roy, wealthStatusInStory, billionaire family member]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wealthStatusInStory Context triple: [Marcia Roy, wealthStatusInStory, billionaire family member]
-
A.
wealthDescribedAs
Indicates that one entity’s wealth is characterized, portrayed, or expressed in terms of another entity or description.
-
B.
isWealthy
chosen
Indicates that an entity possesses a high level of financial resources or assets relative to a given standard.
-
C.
wealthSymbol
Indicates that one entity serves as a representation or sign of wealth for another entity.
-
D.
richIn
Indicates that something contains a high amount or concentration of a particular substance, quality, or resource.
-
E.
usesWealthFor
Indicates that one entity directs or allocates its wealth or financial resources toward another entity or purpose.
- 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_69f76eafe20c8190856d3b996a4c31a7 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb78cbef988190b8f79d946b46e6b2 |
completed | May 6, 2026, 5:22 p.m. |
| PD | Predicate disambiguation | batch_69fb5a9ac5a08190b24ef308963fc52b |
completed | May 6, 2026, 3:13 p.m. |
Created at: May 3, 2026, 4:16 p.m.