Triple
T37229235
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Slate Rock and Gravel Company |
E923085
|
entity |
| Predicate | hasFictionalCorporateLeader |
P67496
|
FINISHED |
| Object | Mr. Slate |
—
|
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: Mr. Slate | Statement: [Slate Rock and Gravel Company, hasFictionalCorporateLeader, Mr. Slate]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFictionalCorporateLeader Context triple: [Slate Rock and Gravel Company, hasFictionalCorporateLeader, Mr. Slate]
-
A.
hasFictionalLeader
chosen
Indicates that an entity is led or governed by a leader who is a fictional character rather than a real person.
-
B.
hasFictionalSpokesperson
Indicates that an entity is represented or promoted by a spokesperson who is a fictional or imaginary character.
-
C.
hasFictionalCorporation
Indicates that an entity is associated with or includes a fictional corporation within its content, setting, or narrative.
-
D.
hasFictionalLeadCharacter
Indicates that a creative work features a particular fictional character as its main or leading protagonist.
-
E.
fictionalOrganizationLeader
Indicates that one entity serves as the leader or head of a fictional organization represented by the other entity.
- 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_69f76ea7f0008190b31b8e30f3d05a71 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a0056174c908190be99c91a70393e47 |
completed | May 10, 2026, 9:55 a.m. |
| PD | Predicate disambiguation | batch_6a00538e7e08819091ecd4316cd641a1 |
completed | May 10, 2026, 9:44 a.m. |
Created at: May 3, 2026, 4:15 p.m.