Triple
T3068275
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sue Storm (Fantastic Four, 2015 film) |
E62157
|
entity |
| Predicate | canRender |
P44227
|
FINISHED |
| Object | herself invisible |
—
|
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: herself invisible | Statement: [Sue Storm (Fantastic Four, 2015 film), canRender, herself invisible]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canRender Context triple: [Sue Storm (Fantastic Four, 2015 film), canRender, herself invisible]
-
A.
canRepresent
Indicates that one entity is capable of serving as a valid stand-in, proxy, or expression for another entity in a given context.
-
B.
canBeDepictedAs
Indicates that one entity is capable of being visually represented or illustrated in the form or style of another entity.
-
C.
renderedUnder
Indicates that one entity was produced, displayed, or executed within the authority, context, or environment provided by another entity.
-
D.
renderedBy
Indicates that something is produced, drawn, or visually generated by a particular agent, tool, or process.
-
E.
renders
Indicates that one entity produces, generates, or visually presents another entity, often by transforming data or instructions into a final displayed or usable form.
- 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_69ad85793e5c8190a358049bc4a98d8c |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada0ffcc208190962cc9edcbf43c31 |
completed | March 8, 2026, 4:17 p.m. |
| PD | Predicate disambiguation | batch_69ad9624b7a0819091d255614f5819ea |
completed | March 8, 2026, 3:30 p.m. |
| PDg | Predicate description generation | batch_69ad97f7630c81908e1ca8a69611cff6 |
completed | March 8, 2026, 3:38 p.m. |
Created at: March 8, 2026, 3:02 p.m.