Triple
T19090902
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tarsem Singh |
E467275
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Mirror Mirror |
—
|
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: Mirror Mirror | Statement: [Tarsem Singh, notableWork, Mirror Mirror]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mirror Mirror Context triple: [Tarsem Singh, notableWork, Mirror Mirror]
-
A.
Mirror Mirror
chosen
Mirror Mirror is a 2012 fantasy comedy film that offers a whimsical, visually stylized retelling of the Snow White fairy tale.
-
B.
Mirror, Mirror
"Mirror, Mirror" is a classic Star Trek: The Original Series episode that introduces the iconic "mirror universe," depicting darker alternate versions of the Enterprise crew.
-
C.
Mirrors
"Mirrors" is a 2008 supernatural horror film starring Amy Smart and Kiefer Sutherland, centered on a haunted department store whose mirrors unleash deadly forces.
-
D.
Mirrors
"Mirrors" is an EP by the British rock band Young Guns, showcasing their melodic, anthemic alternative rock sound.
-
E.
Mirrors
"Mirrors" is a 2013 pop and R&B ballad by Justin Timberlake, known for its reflective lyrics about lasting love and its expansive, multi-part production.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8dd05ac4c8190b1967d8f97f3fb2f |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e34b6b348190bb868356ed8b655a |
completed | April 20, 2026, 8:26 a.m. |
Created at: April 10, 2026, 12:04 p.m.