Triple
T17746200
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matt Murdock |
E442996
|
entity |
| Predicate | formerCostumeColor |
P11861
|
FINISHED |
| Object | yellow |
—
|
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 | Statement: [Matt Murdock, formerCostumeColor, yellow]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerCostumeColor Context triple: [Matt Murdock, formerCostumeColor, yellow]
-
A.
originalCostumeColor
chosen
Indicates the color that a costume originally had before any changes, damage, or alterations.
-
B.
colorAssociatedWithCostume
Indicates that a particular color is thematically or typically linked to a specific costume.
-
C.
formerColor
Indicates that an entity previously had a certain color, but no longer has that color now.
-
D.
costume
Indicates that one entity is wearing, dressed in, or outfitted with the other entity as a costume.
-
E.
costumeContext
Indicates the situational or narrative context in which a costume is used, such as the event, setting, or role it is associated with.
- 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_69d8b9ed3a2081909b2ec0d4dd2f4c37 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e47ad26940819090696c2cb86fd606 |
completed | April 19, 2026, 6:48 a.m. |
| PD | Predicate disambiguation | batch_69e3cde9dc288190af0e2198487f2051 |
completed | April 18, 2026, 6:31 p.m. |
Created at: April 10, 2026, 10:09 a.m.