Triple
T20879209
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Public Enemy No. 1 (FBI label for John Dillinger) |
E514098
|
entity |
| Predicate | appliedToPersonDeathYear |
P16526
|
FINISHED |
| Object | 1934 |
—
|
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: 1934 | Statement: [Public Enemy No. 1 (FBI label for John Dillinger), appliedToPersonDeathYear, 1934]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appliedToPersonDeathYear Context triple: [Public Enemy No. 1 (FBI label for John Dillinger), appliedToPersonDeathYear, 1934]
-
A.
yearOfDeath
chosen
Indicates the specific year in which an entity (typically a person or organism) died.
-
B.
deathYearApproximate
Indicates that the year of an entity’s death is known only approximately rather than as an exact calendar year.
-
C.
compilerDeathYearGregorian
Indicates the year, in the Gregorian calendar, in which the compiler of a work died.
-
D.
deathYearInferredFrom
Indicates that an entity’s year of death is not directly known but has been deduced based on other available information or evidence.
-
E.
dateOfDeath
Indicates the specific date on which an individual or entity died.
- 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_69e0b4f733f081908a401c0b7beb0b9f |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c678b394819096a17de9e04cd74f |
completed | April 21, 2026, 12:36 a.m. |
| PD | Predicate disambiguation | batch_69e5c9a8dc148190b33ff51894e2a8f9 |
completed | April 20, 2026, 6:37 a.m. |
Created at: April 16, 2026, 12:45 p.m.