Triple
T33599329
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Juliet (Love Actually) |
E860671
|
entity |
| Predicate | weddingVideoRecordedBy |
P141703
|
FINISHED |
| Object | Mark (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: Mark (Love Actually) | Statement: [Juliet (Love Actually), weddingVideoRecordedBy, Mark (Love Actually)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: weddingVideoRecordedBy Context triple: [Juliet (Love Actually), weddingVideoRecordedBy, Mark (Love Actually)]
-
A.
wasRecordedBy
chosen
Indicates that an event, observation, or piece of data was captured or documented by a specific agent, instrument, or recording process.
-
B.
hasWeddingSceneWith
Indicates that two entities appear together in a wedding scene within the same context or work.
-
C.
weddingRole
Indicates the specific role or function an entity has in the context of a wedding event.
-
D.
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).
-
E.
bride
Indicates that an entity is a woman who is getting married or has just been married in relation to a wedding event or spouse.
- 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_69f6f7a8225881908c37c08c3cc86928 |
completed | May 3, 2026, 7:22 a.m. |
| PD | Predicate disambiguation | batch_69f6f6632dfc8190af85e258c8519207 |
completed | May 3, 2026, 7:16 a.m. |
Created at: May 1, 2026, 1:41 a.m.