Triple
T36481283
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wormwood: Gentleman Corpse |
E898821
|
entity |
| Predicate | hasProtagonistBody |
P185186
|
FINISHED |
| Object | reanimated corpse |
—
|
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: reanimated corpse | Statement: [Wormwood: Gentleman Corpse, hasProtagonistBody, reanimated corpse]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasProtagonistBody Context triple: [Wormwood: Gentleman Corpse, hasProtagonistBody, reanimated corpse]
-
A.
hasProtagonist
Indicates that a work of narrative has a main character who serves as its central focus or driving agent.
-
B.
hasSpiritProtagonist
Indicates that the primary or central character in a narrative is a spirit or non-corporeal being.
-
C.
hasMainProtagonistTrait
Indicates that the specified trait is a defining or primary characteristic of the main protagonist.
-
D.
hasProtagonistClass
chosen
Indicates that a work’s main character belongs to a specified class or category.
-
E.
hasProtagonistFromSource
Indicates that a work’s main character originates from, or is derived from, a specified source (such as another work, franchise, or medium).
- 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_69f76e5a0e088190a2b6706aeb41723c |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037c8e2c648190a65fc9c7872861af |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a0bf4b88190bdcfae9a14b51f0a |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:10 p.m.