Triple
T24087009
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roscoe "Fatty" Arbuckle |
E596674
|
entity |
| Predicate | directedUnderPseudonym |
P155034
|
FINISHED |
| Object | William Goodrich |
—
|
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: William Goodrich | Statement: [Roscoe "Fatty" Arbuckle, directedUnderPseudonym, William Goodrich]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: directedUnderPseudonym Context triple: [Roscoe "Fatty" Arbuckle, directedUnderPseudonym, William Goodrich]
-
A.
revealedAsPseudonymIn
Indicates that one identity or name is disclosed or recognized as a pseudonym within a particular context, work, or source.
-
B.
firstPublishedUnderPseudonym
Indicates that a work’s initial publication occurred under a pseudonym rather than the creator’s real name.
-
C.
pseudonymCoinedBy
Indicates that a particular pseudonym was created or invented by a specific agent or source.
-
D.
pseudonymInspiredBy
Indicates that a pseudonym was chosen or created based on, or in homage to, another name, person, work, or concept.
-
E.
pseudonymOfWriter
Indicates that one entity is a pseudonym used by a writer who is represented by the other entity.
- 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_69e288c4638c81909bacc28a1e3d436b |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1dc2b555481909ffcd2898fdd51fa |
completed | April 29, 2026, 10:23 a.m. |
| PD | Predicate disambiguation | batch_69f17651458c8190bbfd301883e46085 |
completed | April 29, 2026, 3:09 a.m. |
| PDg | Predicate description generation | batch_69f17b58012c81909106b332db399023 |
completed | April 29, 2026, 3:30 a.m. |
Created at: April 17, 2026, 10:45 p.m.