Triple
T33599374
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mark (Love Actually) |
E860672
|
entity |
| Predicate | recordsVideoOf |
P83514
|
FINISHED |
| Object | Juliet (Love Actually) |
—
|
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: Juliet (Love Actually) | Statement: [Mark (Love Actually), recordsVideoOf, Juliet (Love Actually)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: recordsVideoOf Context triple: [Mark (Love Actually), recordsVideoOf, Juliet (Love Actually)]
-
A.
videoIn
Indicates that one entity is a video that is contained within, embedded in, or associated as input to another entity.
-
B.
hasVideoRecording
chosen
Indicates that there exists an associated video recording capturing or documenting the referenced entity or event.
-
C.
recordingOf
Indicates that one entity is an audio or video capture or performance that documents, represents, or preserves another entity (such as a work, event, or expression).
-
D.
storesVideoAs
Indicates that one entity keeps or maintains another entity in the form of a video recording.
-
E.
legendRecordedFrom
Indicates that a legend or traditional story was documented or collected from a particular source, such as a person, group, or location.
- 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_69f3497f35908190a2e9bbb9b96c7a3f |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fd5bf69acc819092a01e4259785dc3 |
completed | May 8, 2026, 3:43 a.m. |
| PD | Predicate disambiguation | batch_69fd59b3f4ac8190a7f9dd3142da6e09 |
completed | May 8, 2026, 3:34 a.m. |
Created at: May 1, 2026, 1:41 a.m.