Triple
T2865049
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kate Mara |
E63418
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Megan Leavey |
E62152
|
NE 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: Megan Leavey | Statement: [Kate Mara, notableWork, Megan Leavey]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Megan Leavey Context triple: [Kate Mara, notableWork, Megan Leavey]
-
A.
Megan Leavey
chosen
Megan Leavey is a 2017 biographical war drama film about a U.S. Marine and her military working dog during the Iraq War.
-
B.
Lauren Mara
Lauren Mara is a member of the Mara family, known for its long-standing ownership and leadership of the New York Giants NFL franchise.
-
C.
Yvette Marie Stevens
Yvette Marie Stevens is the birth name of Chaka Khan, the iconic American singer known as the "Queen of Funk."
-
D.
Patricia Knox
Patricia Knox is a person notable enough to be recognized as a bearer of the surname Knox.
-
E.
Michael S. Murphy
Michael S. Murphy is a film and television editor best known for his work on the 1997 musical fantasy film "Rodgers & Hammerstein's Cinderella."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ab4c42fb8c8190b36e161d47c03b81 |
completed | March 6, 2026, 9:50 p.m. |
| NER | Named-entity recognition | batch_69abdfb9e64c819087b1a47caeb174d5 |
completed | March 7, 2026, 8:20 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b01da458ec8190ae07237d7e23b302 |
completed | March 10, 2026, 1:33 p.m. |
Created at: March 6, 2026, 10:02 p.m.