Triple
T20517661
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tom Bernard |
E503721
|
entity |
| Predicate | sharesPositionWith |
P91972
|
FINISHED |
| Object | Marcie Bloom |
—
|
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: Marcie Bloom | Statement: [Tom Bernard, sharesPositionWith, Marcie Bloom]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marcie Bloom Context triple: [Tom Bernard, sharesPositionWith, Marcie Bloom]
-
A.
Marcie Bloom
chosen
Marcie Bloom is a film executive and co-founder of Sony Pictures Classics, known for her influential role in acquiring and distributing acclaimed independent and foreign films.
-
B.
Lisa Blum
Lisa Blum is a film producer known for her work on the horror-comedy movie "A Haunted House."
-
C.
Lisa Bluder
Lisa Bluder is a longtime head coach of the University of Iowa women's basketball team, known for leading the Hawkeyes to national prominence behind star players like Caitlin Clark.
-
D.
Lisa Loomer
Lisa Loomer is an American playwright and screenwriter known for her socially conscious works in theater and film.
-
E.
Stacey Mindich
Stacey Mindich is a Tony Award–winning American theater producer best known for shepherding the hit Broadway musical "Dear Evan Hansen."
- 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_69e0b4b2aa788190ae9eb37c1d73b1f1 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69f42db688190a3ccfba5601e8bf3 |
completed | April 20, 2026, 9:48 p.m. |
Created at: April 16, 2026, 11:36 a.m.