Triple
T21970965
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John and Mary |
E542585
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Olympia Dukakis |
—
|
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: Olympia Dukakis | Statement: [John and Mary, starring, Olympia Dukakis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Olympia Dukakis Context triple: [John and Mary, starring, Olympia Dukakis]
-
A.
Olympia Dukakis
chosen
Olympia Dukakis was an American stage and screen actress best known for her Academy Award–winning supporting role in the romantic comedy film "Moonstruck."
-
B.
Phylis Morrison
Phylis Morrison was an American science educator and writer known for her collaborations with physicist Philip Morrison on popular science books and television programs.
-
C.
Ellen Holbrook
Ellen Holbrook is a notable individual associated with the Holbrook name, recognized as a distinguished bearer of this surname.
-
D.
Sandy Dennis
Sandy Dennis was an American stage and film actress known for her intense, neurotic character portrayals and her Academy Award–winning performance in "Who's Afraid of Virginia Woolf?".
-
E.
Shirley MacLaine
Shirley MacLaine is an acclaimed American actress, dancer, and author known for her versatile film roles, spiritual writings, and a career spanning over six decades.
- 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_69e0c48070988190909db97667b9a0ac |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f12484b83081908c08e3285e0b14a9 |
completed | April 28, 2026, 9:20 p.m. |
Created at: April 16, 2026, 8:02 p.m.