Triple
T7969468
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hatbox Ghost |
E185286
|
entity |
| Predicate | hasCatchFeature |
P80065
|
FINISHED |
| Object | disappearing head illusion |
—
|
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: disappearing head illusion | Statement: [Hatbox Ghost, hasCatchFeature, disappearing head illusion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCatchFeature Context triple: [Hatbox Ghost, hasCatchFeature, disappearing head illusion]
-
A.
hasCoverFeature
Indicates that one entity serves as a prominent or featured element on the cover of another entity (such as a publication, product, or media item).
-
B.
hasTrailFeature
Indicates that a trail possesses or is characterized by a specific feature or attribute.
-
C.
hasFeatureCode
Indicates that an entity is associated with a specific feature identifier or code that characterizes one of its properties or attributes.
-
D.
hasMountingFeature
Indicates that one entity includes or provides a structural feature intended for mounting or attaching another entity.
-
E.
hasFrontFeature
Indicates that an entity possesses a specific characteristic, component, or attribute located on its front side.
- F. None of above. chosen
Provenance (4 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_69ca8297699481909b75a405f01e03af |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3bd1c9a081909759e5bf5237204e |
completed | March 31, 2026, 3:13 a.m. |
| PD | Predicate disambiguation | batch_69cb047a8e4c81909b79e0f0bf56440c |
completed | March 30, 2026, 11:17 p.m. |
| PDg | Predicate description generation | batch_69cb14bbbacc81909c6cf8ec35314bbb |
completed | March 31, 2026, 12:26 a.m. |
Created at: March 30, 2026, 5:13 p.m.