Triple
T37157960
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Law & Order: Criminal Intent theme |
E920560
|
entity |
| Predicate | openingSequenceElement |
P193755
|
FINISHED |
| Object | title card |
—
|
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: title card | Statement: [Law & Order: Criminal Intent theme, openingSequenceElement, title card]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: openingSequenceElement Context triple: [Law & Order: Criminal Intent theme, openingSequenceElement, title card]
-
A.
openingSequence
Indicates the initial ordered set of actions or events that begin a process, performance, or interaction.
-
B.
openingSequenceType
Indicates the specific kind or category of an opening sequence associated with an entity or event.
-
C.
openingSequenceWorkPerformed
Indicates that a specific work is performed as the opening sequence of a larger performance or program.
-
D.
openingSequenceFormat
Indicates the specific structural or stylistic format used for an opening sequence in a work or presentation.
-
E.
openingSequenceDepicts
Indicates that the opening sequence of a work visually or narratively portrays a particular event, situation, or subject.
- 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_69f76ea0429081908c711b55599eac3c |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fd509e6bc08190b263923c2f40fea3 |
completed | May 8, 2026, 2:55 a.m. |
| PD | Predicate disambiguation | batch_69fd4fd1a58881909d4b84de1b24e380 |
completed | May 8, 2026, 2:52 a.m. |
| PDg | Predicate description generation | batch_69fd509cdc5c8190a5f2c451bc0d0b25 |
completed | May 8, 2026, 2:55 a.m. |
Created at: May 3, 2026, 4:15 p.m.