Triple
T30596505
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kaecilius |
E778801
|
entity |
| Predicate | eyeMarkings |
P51923
|
FINISHED |
| Object | cracked purple markings around the eyes (MCU) |
—
|
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: cracked purple markings around the eyes (MCU) | Statement: [Kaecilius, eyeMarkings, cracked purple markings around the eyes (MCU)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eyeMarkings Context triple: [Kaecilius, eyeMarkings, cracked purple markings around the eyes (MCU)]
-
A.
eggMarkings
Indicates that one entity bears or displays specific markings or patterns on its eggs in relation to another entity or context.
-
B.
coatMarkings
Indicates how an entity’s coat is patterned or marked, such as stripes, spots, or other distinctive visual markings.
-
C.
eyeCharacteristic
chosen
Indicates a relationship where an entity possesses a specific attribute, feature, or quality of its eyes.
-
D.
facialMarkings
Indicates that one entity has distinctive marks, patterns, or features on its face in relation to another entity or context.
-
E.
leafMarkings
Indicates the presence, pattern, or characteristics of markings found on the surface of a leaf.
- 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_69f224a1570c8190a85d3ac330479a79 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6897fc2e881909e2bd183eb7fddc9 |
completed | May 2, 2026, 11:32 p.m. |
| PD | Predicate disambiguation | batch_69f67e448a9c8190b591374d98799fe3 |
completed | May 2, 2026, 10:44 p.m. |
Created at: April 29, 2026, 8:24 p.m.