Triple
T32937383
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Sin of Harold Diddlebock |
E842568
|
entity |
| Predicate | starsLaterCareerRoleOf |
P175420
|
FINISHED |
| Object | Harold Lloyd |
—
|
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: Harold Lloyd | Statement: [The Sin of Harold Diddlebock, starsLaterCareerRoleOf, Harold Lloyd]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: starsLaterCareerRoleOf Context triple: [The Sin of Harold Diddlebock, starsLaterCareerRoleOf, Harold Lloyd]
-
A.
creditedRoleOf
Indicates that a particular role or position is formally acknowledged as being held or performed by a specific entity in a credit or attribution context.
-
B.
followedByRoleInCareerOf
Indicates that one role or position directly succeeds another in the sequence of roles within a single entity’s career.
-
C.
starOccupation
Indicates that an entity is the primary or featured performer in a particular occupation, role, or professional capacity.
-
D.
laterAffiliationInFilm
Indicates that an entity becomes affiliated with another entity at a later point within the timeline or narrative of a film.
-
E.
laterCareerWorkOf
Indicates that one work represents a creator’s later career output in relation to another work or to their overall body of work.
- 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_69f34949727c81909d195c97de3341c8 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6d1d916f881909575c2b22c416a5b |
completed | May 3, 2026, 4:40 a.m. |
| PD | Predicate disambiguation | batch_69f6cfe5f93c8190995c53dbbe380a32 |
completed | May 3, 2026, 4:32 a.m. |
| PDg | Predicate description generation | batch_69f6d0d331dc8190be5aa6bfc6365e67 |
completed | May 3, 2026, 4:36 a.m. |
Created at: May 1, 2026, 1:20 a.m.