Triple
T27280916
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dwight (The Walking Dead) |
E688326
|
entity |
| Predicate | visualMarking |
P32310
|
FINISHED |
| Object | burned left eye area |
—
|
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: burned left eye area | Statement: [Dwight (The Walking Dead), visualMarking, burned left eye area]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: visualMarking Context triple: [Dwight (The Walking Dead), visualMarking, burned left eye area]
-
A.
distinctiveMarking
chosen
Indicates that one entity bears a unique or distinguishing visual feature or pattern that sets it apart from others.
-
B.
lightingMarks
Indicates that one entity applies or provides lighting effects or illumination to another entity or location.
-
C.
markingFeature
Indicates a feature that serves as a distinguishing mark or identifier associated with an entity.
-
D.
billMarkings
Indicates a relationship where specific markings or patterns are present on or associated with a bill (such as a beak or financial document).
-
E.
seedMarking
Indicates that an entity bears or applies a specific mark, pattern, or label associated with seeds.
- 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_69ef355998e08190bdff849e8f33adce |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69f6352fdb788190b9bad30243690743 |
completed | May 2, 2026, 5:32 p.m. |
| PD | Predicate disambiguation | batch_69f631850ae08190a0ba51e4f1e4ccb3 |
completed | May 2, 2026, 5:16 p.m. |
Created at: April 27, 2026, 11:07 a.m.