Triple
T19517177
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Constance Spano |
E488306
|
entity |
| Predicate | worksWith |
P398
|
FINISHED |
| Object | David Levinson |
—
|
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: David Levinson | Statement: [Constance Spano, worksWith, David Levinson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Levinson Context triple: [Constance Spano, worksWith, David Levinson]
-
A.
David Levinson
David Levinson is the brilliant, neurotic computer expert and satellite technician Jeff Goldblum plays in the science-fiction film "Independence Day."
-
B.
David Levinson
David Levinson was an American Jewish fraternity leader best known for founding the collegiate social fraternity Sigma Alpha Mu in the early 20th century.
-
C.
David Levinson
David Levinson is a screenwriter known for his work on the 2018 film "Welcome Home."
-
D.
Paul F. Edwards
Paul F. Edwards is a television and film screenwriter best known for his work on the acclaimed American Civil War miniseries "North and South."
-
E.
Charles F. Wennerstrum
Charles F. Wennerstrum was an American judge best known for serving as a presiding judge at one of the Subsequent Nuremberg Trials following World War II.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide. chosen
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_69d8e8da8bec819081f400199491ccc3 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6359ca7648190804c4d655170fda3 |
completed | April 20, 2026, 2:18 p.m. |
Created at: April 10, 2026, 1:40 p.m.