Triple
T2060832
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Metamorphoses |
E45784
|
entity |
| Predicate | author |
P4
|
FINISHED |
| Object | Mary Zimmerman |
E338441
|
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: Mary Zimmerman | Statement: [Metamorphoses, author, Mary Zimmerman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mary Zimmerman Context triple: [Metamorphoses, author, Mary Zimmerman]
-
A.
Mary Zimmerman
chosen
Mary Zimmerman is an acclaimed American theatre director and playwright known for her visually inventive stage adaptations of classic works and myths.
-
B.
Amy Landecker
Amy Landecker is an American actress best known for her role as Sarah Pfefferman on the television series "Transparent."
-
C.
Melissa Mathison
Melissa Mathison was an American screenwriter best known for writing the screenplay for Steven Spielberg’s film "E.T. the Extra-Terrestrial."
-
D.
Lila Hotz
Lila Hotz was the first wife of American magazine magnate Henry Luce, co-founder of Time Inc.
-
E.
Janel Moloney
Janel Moloney is an American actress best known for her role as Donna Moss on the political drama television series "The West Wing."
- 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_69a8891a19508190a12ef1e192308dcb |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abb9d0ecf08190aec20338a6ba9911 |
completed | March 7, 2026, 5:38 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b276a3cfa48190b0ecee43d24046e6 |
completed | March 12, 2026, 8:17 a.m. |
Created at: March 4, 2026, 7:40 p.m.