Triple
T13833056
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BlacKkKlansman (film score) |
E332452
|
entity |
| Predicate | usedToUnderscore |
P109712
|
FINISHED |
| Object | drama in BlacKkKlansman |
—
|
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: drama in BlacKkKlansman | Statement: [BlacKkKlansman (film score), usedToUnderscore, drama in BlacKkKlansman]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedToUnderscore Context triple: [BlacKkKlansman (film score), usedToUnderscore, drama in BlacKkKlansman]
-
A.
designedToUnderscore
chosen
Indicates that something is intentionally created or arranged in order to emphasize, highlight, or draw special attention to another thing.
-
B.
transformVariableName
Indicates converting a variable’s name from one format or style to another according to specified naming rules.
-
C.
usedAsSuffixTo
Indicates that one entity functions as a suffix appended to another entity, typically to modify or extend its meaning.
-
D.
exportName
Indicates that one entity is exported under a specific name or label in relation to another context or system.
-
E.
underlines
Indicates that one entity draws or applies a line beneath another entity, typically to emphasize or highlight it.
- 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_69d81c5ae7c88190b0dd41bdafeb5999 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de029a34bc8190ae892ef7b09fc9e9 |
completed | April 14, 2026, 9:02 a.m. |
| PD | Predicate disambiguation | batch_69dbc86668e08190ba9135d1c3f38d35 |
completed | April 12, 2026, 4:29 p.m. |
Created at: April 9, 2026, 10:13 p.m.