Triple
T28196935
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Flash |
E716472
|
entity |
| Predicate | featuresSpokenDialogueBy |
P124214
|
FINISHED |
| Object | Max von Sydow |
—
|
NE NERFINISHED |
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: Max von Sydow | Statement: [Flash, featuresSpokenDialogueBy, Max von Sydow]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresSpokenDialogueBy Context triple: [Flash, featuresSpokenDialogueBy, Max von Sydow]
-
A.
dialogueFeature
Indicates that one entity exhibits or involves a particular characteristic, property, or element of a dialogue or conversational exchange with another entity.
-
B.
usesSpokenDialogue
Indicates that one entity communicates with another through spoken dialogue as the primary mode of interaction.
-
C.
speakerFeatures
Indicates that certain characteristics, attributes, or properties are associated with a speaker in a given context.
-
D.
featuresSpokenOrChildVocal
chosen
Indicates that the subject has characteristics related to spoken language or vocalizations produced by a child.
-
E.
featuresDialect
Indicates that something includes or exhibits a particular dialect as one of its linguistic characteristics.
- 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_69efd6b612f48190a72012b520afbd10 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69fe59d11e9881909d2f33b7c717030e |
completed | May 8, 2026, 9:46 p.m. |
| PD | Predicate disambiguation | batch_69fe394fdfbc8190a931926ae3635cbf |
completed | May 8, 2026, 7:28 p.m. |
Created at: April 27, 2026, 10:28 p.m.