Triple
T32188815
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roark Jr. |
E822178
|
entity |
| Predicate | resultOfBodyModification |
P99916
|
FINISHED |
| Object | yellow skin and deformity |
—
|
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: yellow skin and deformity | Statement: [Roark Jr., resultOfBodyModification, yellow skin and deformity]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: resultOfBodyModification Context triple: [Roark Jr., resultOfBodyModification, yellow skin and deformity]
-
A.
operatedOnBody
Indicates that a medical or surgical procedure was performed on a particular body or body part.
-
B.
modifiesBody
Indicates that one entity alters, changes, or affects the physical body or bodily state of another entity.
-
C.
bodyTransformation
chosen
Indicates a change in an entity’s physical form, structure, or appearance into a different bodily state.
-
D.
bodyModificationReason
Indicates the reason or motivation behind a particular body modification performed on an entity.
-
E.
bodyPartsTransformedInto
Indicates that one or more body parts of an entity are changed or converted into different body parts or forms.
- 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_69f3490819cc81909bae1f8ce99423c5 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f9fd6834cc8190aa27153d6a99f3bb |
completed | May 5, 2026, 2:23 p.m. |
| PD | Predicate disambiguation | batch_69f7cf769338819092a5f42653dcc956 |
completed | May 3, 2026, 10:43 p.m. |
Created at: May 1, 2026, 12:35 a.m.