Triple
T35330755
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Candy Man |
E1020308
|
entity |
| Predicate | appliesToPersonBornIn |
P147470
|
FINISHED |
| Object | 1985 |
—
|
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: 1985 | Statement: [Candy Man, appliesToPersonBornIn, 1985]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appliesToPersonBornIn Context triple: [Candy Man, appliesToPersonBornIn, 1985]
-
A.
appliedToPersonBornIn
chosen
Indicates that something (such as a rule, action, status, or condition) is applied specifically to a person who was born in a particular place.
-
B.
appliesToPersonBirthName
Indicates that the referenced value is used as the birth name of the specified person.
-
C.
refersToPersonBornOn
Indicates that one entity makes reference to, or is associated with, a specific person who was born on a given date.
-
D.
appliesToPersonNationality
Indicates that something is relevant or applicable specifically to a person’s nationality.
-
E.
namedForPersonBornInArea
Indicates that something is named after a person who was born in the specified geographic area.
- 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_69f76deacf4481908e7735a5a7715b0a |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69ff3fb2318c81908a46c2f513608935 |
completed | May 9, 2026, 2:07 p.m. |
| PD | Predicate disambiguation | batch_69ff3e96dcc48190819f6204680d84aa |
completed | May 9, 2026, 2:03 p.m. |
Created at: May 3, 2026, 4:03 p.m.