Triple
T11984206
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Edward Bloom |
E285234
|
entity |
| Predicate | deathSceneDepictedAs |
P29944
|
FINISHED |
| Object | transformation into a big fish |
—
|
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: transformation into a big fish | Statement: [Edward Bloom, deathSceneDepictedAs, transformation into a big fish]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: deathSceneDepictedAs Context triple: [Edward Bloom, deathSceneDepictedAs, transformation into a big fish]
-
A.
deathSceneWork
Indicates that a creative work features or depicts the scene in which a character dies.
-
B.
deathDescribedIn
Indicates that a person's death is documented, narrated, or otherwise detailed within a particular source or description.
-
C.
deathDescribedAs
chosen
Indicates that one entity characterizes, portrays, or refers to another entity’s death using a particular description, metaphor, or wording.
-
D.
deathApprox
Indicates that an entity’s death occurred at an approximate, rather than exact, time or date.
-
E.
deathBy
Indicates a relationship where one entity’s death is caused by another entity, event, or factor.
- 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_69d6ab44a77c8190a652f4b27164e4ef |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d903acbb9081908fe7f8360057785c |
completed | April 10, 2026, 2:05 p.m. |
| PD | Predicate disambiguation | batch_69d902abca70819098291aa51b593708 |
completed | April 10, 2026, 2:01 p.m. |
Created at: April 8, 2026, 9:46 p.m.