Triple
T20389755
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Demolition |
E498054
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Molly Smith |
—
|
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 Smith | Statement: [Demolition, producer, Molly Smith]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Molly Smith Context triple: [Demolition, producer, Molly Smith]
-
A.
Molly Smith
chosen
Molly Smith is an American film producer known for her work on acclaimed movies such as the crime thriller "Sicario."
-
B.
Molly Smith
Molly Smith is a daughter of FedEx founder and CEO Frederick W. Smith.
-
C.
Molly Mickler Smith
Molly Mickler Smith is a film producer known for her work on the romantic comedy "Something Borrowed."
-
D.
Molly Allen
Molly Allen is a film producer known for her work on the 2014 comedy-drama "Chef."
-
E.
Molly Arkin
Molly Arkin is the daughter of American actor and director Adam Arkin.
- 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_69e0b4a71ebc8190b153a36c738730f4 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6790e65a081909832855758fffd14 |
completed | April 20, 2026, 7:05 p.m. |
Created at: April 16, 2026, 11:28 a.m.