Triple
T17036193
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | I Am Dead |
E413325
|
entity |
| Predicate | supportingCharacterType |
P60013
|
FINISHED |
| Object | ghost dog |
—
|
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: ghost dog | Statement: [I Am Dead, supportingCharacterType, ghost dog]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportingCharacterType Context triple: [I Am Dead, supportingCharacterType, ghost dog]
-
A.
supportingCharacter
Indicates that one entity plays a secondary or assisting role in the story or context relative to another primary entity.
-
B.
supportingCharacterPortrayedBy
Indicates that a supporting (non-leading) character in a work is portrayed or acted by a specific performer.
-
C.
secondaryProtagonistType
Indicates the role or category of a work’s secondary main character in relation to the primary protagonist.
-
D.
typeOfCharacter
chosen
Indicates that one entity is a specific kind or category of character in relation to another entity.
-
E.
relatedCharacterType
Indicates that one character has a specified type of relationship or role in connection to another character.
- 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_69d886cd18288190b006abab23f811b7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d8f26f50819085dfd0fbecd6394d |
completed | April 18, 2026, 7:18 p.m. |
| PD | Predicate disambiguation | batch_69e35d5be7f48190af9db67a1e23850f |
completed | April 18, 2026, 10:30 a.m. |
Created at: April 10, 2026, 5:33 a.m.