Triple
T22767203
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fresh Horses |
E563157
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Molly Hagan |
—
|
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: Molly Hagan | Statement: [Fresh Horses, castMember, Molly Hagan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Molly Hagan Context triple: [Fresh Horses, castMember, Molly Hagan]
-
A.
Molly Hagan
chosen
Molly Hagan is an American actress known for her extensive work in film and television, including roles in projects like "Election," "iZombie," and "Walker."
-
B.
Molly Allen
Molly Allen is a film producer known for her work on the 2014 comedy-drama "Chef."
-
C.
Stephanie McCord
Stephanie McCord is a fictional character in the political drama series "Madam Secretary," known as the daughter of U.S. Secretary of State (and later President) Elizabeth McCord.
-
D.
Molly Smith
Molly Smith is a daughter of FedEx founder and CEO Frederick W. Smith.
-
E.
Molly Smith
Molly Smith is an American film producer known for her work on acclaimed movies such as the crime thriller "Sicario."
- 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_69e24552e11c81909c2d61578a558bd7 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17a80e2688190b76844c408929d32 |
completed | April 29, 2026, 3:26 a.m. |
Created at: April 17, 2026, 3:27 p.m.