Triple
T32554479
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mad Ghost Productions |
E832060
|
entity |
| Predicate | hasRoleOfFounder |
P7059
|
FINISHED |
| Object | Geoff Johns |
—
|
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: Geoff Johns | Statement: [Mad Ghost Productions, hasRoleOfFounder, Geoff Johns]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRoleOfFounder Context triple: [Mad Ghost Productions, hasRoleOfFounder, Geoff Johns]
-
A.
workIncludesRoleOfFounder
Indicates that a work involves or credits an entity in the specific role of founder.
-
B.
hasCoFounderRole
Indicates that an entity holds or is assigned the role of co-founder in relation to another entity (such as an organization or project).
-
C.
founderRole
chosen
Indicates that an entity serves as a founder in relation to another entity, specifying the role or capacity in which they established it.
-
D.
hasCoFounderRoleOf
Indicates that one entity holds the role or position of co-founder in relation to another entity, such as an organization or venture.
-
E.
ownerOrFounder
Indicates that an entity either owns or has founded another entity, capturing both ownership and founding relationships.
- 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_69f34926b9848190ace47d2dd0a0de7c |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fd9ff026a48190bfec33deeb3b2c43 |
completed | May 8, 2026, 8:33 a.m. |
| PD | Predicate disambiguation | batch_69fd97d805bc8190ba12f429d3ad04c7 |
completed | May 8, 2026, 7:59 a.m. |
Created at: May 1, 2026, 1:02 a.m.