Triple
T29824883
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bannik |
E757351
|
entity |
| Predicate | perceivedAppearance |
P311
|
FINISHED |
| Object | small old man covered in steam or soot in some tales |
—
|
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: small old man covered in steam or soot in some tales | Statement: [Bannik, perceivedAppearance, small old man covered in steam or soot in some tales]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: perceivedAppearance Context triple: [Bannik, perceivedAppearance, small old man covered in steam or soot in some tales]
-
A.
perceivedAttribute
Indicates that one entity recognizes, interprets, or assigns a particular attribute or quality to another entity.
-
B.
appearance
chosen
Indicates how something looks or seems to an observer, including its visible form, condition, or outward impression.
-
C.
publicAppearance
Indicates that an entity participates in or is present at an event or situation that is open or visible to the general public.
-
D.
photographicAppearance
Indicates that one entity visually appears in a photograph or photographic representation of another entity.
-
E.
segmentAppearance
Indicates how a particular segment is visually or perceptually presented or manifested.
- 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_69f22457c84c8190a6d9f56bc74082a9 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f69dfdda708190be290c7bec205445 |
completed | May 3, 2026, 12:59 a.m. |
| PD | Predicate disambiguation | batch_69f69d1a37e081908d1d86b90ff502bd |
completed | May 3, 2026, 12:55 a.m. |
Created at: April 29, 2026, 5:31 p.m.