Triple
T22079306
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Obvious Child |
E545603
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Elisabeth Holm |
—
|
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: Elisabeth Holm | Statement: [Obvious Child, screenwriter, Elisabeth Holm]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Elisabeth Holm Context triple: [Obvious Child, screenwriter, Elisabeth Holm]
-
A.
Elisabeth Holm
chosen
Elisabeth Holm is an American film producer and screenwriter best known for her collaborations with director Gillian Robespierre on acclaimed indie films like "Obvious Child" and "Landline."
-
B.
Mona Lindholm
Mona Lindholm is known as the wife of acclaimed American cinematographer Owen Roizman.
-
C.
Catherine Olsson
Catherine Olsson is a researcher and entrepreneur known for her work in AI safety and interpretability, including co-founding the AI company Anthropic.
-
D.
Laura Holmgren
Laura Holmgren is the wife of American political scientist and author Francis Fukuyama.
-
E.
Tora Parsberg
Tora Parsberg is a character from the Danish film "Paul Lange og Tora Parsberg," which centers on political and personal drama in early 20th-century Denmark.
- 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_69e11e3523488190badd54b5d580c00d |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f128b43df0819090c248ded98fad12 |
completed | April 28, 2026, 9:37 p.m. |
Created at: April 16, 2026, 8:28 p.m.