Triple
T3432378
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael J. Fox |
E72367
|
entity |
| Predicate | publiclyDisclosedCondition |
P5035
|
FINISHED |
| Object | Parkinson's disease |
—
|
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: Parkinson's disease | Statement: [Michael J. Fox, publiclyDisclosedCondition, Parkinson's disease]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: publiclyDisclosedCondition Context triple: [Michael J. Fox, publiclyDisclosedCondition, Parkinson's disease]
-
A.
publiclyDisplayed
Indicates that something is shown or made visible in a public context or setting, accessible to people at large.
-
B.
discloses
chosen
Indicates that one entity reveals, makes known, or provides previously non-public information to another entity or to the public.
-
C.
revealedBefore
Indicates that one entity becomes known, disclosed, or made apparent earlier in time than another entity.
-
D.
disclosureLevel
Indicates the extent or degree to which information is revealed, shared, or made accessible in a given context.
-
E.
requiresSourceDisclosure
Indicates that performing or using something is contingent on revealing or making known the origin or source from which it was derived.
- 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_69ad85ae14308190bcbc25cfa0246c0b |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb9c077d48190bee40795cab3e422 |
completed | March 8, 2026, 6:02 p.m. |
| PD | Predicate disambiguation | batch_69adae00ad588190bef24373b58a2e1a |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:15 p.m.