Triple
T1731561
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ruth Gordon |
E37820
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Jed Harris |
E34106
|
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: Jed Harris | Statement: [Ruth Gordon, spouse, Jed Harris]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jed Harris Context triple: [Ruth Gordon, spouse, Jed Harris]
-
A.
Jed Harris
chosen
Jed Harris was a prominent American theatrical producer and director known for staging influential Broadway productions in the mid-20th century.
-
B.
Jon Harris
Jon Harris is a film editor known for his work on major feature films such as "127 Hours," "The Descent," and "Gravity."
-
C.
David Harris
David Harris is a former NFL linebacker best known as the durable, tackling anchor of the New York Jets’ defense during the Rex Ryan era.
-
D.
David Harris
David Harris is an American anti–Vietnam War activist and writer known for his draft resistance and brief marriage to folk singer Joan Baez.
-
E.
Michael Filerman
Michael Filerman was an American television producer best known for developing and producing popular prime-time soap operas during the 1970s and 1980s.
- 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_69a8861cc6ac8190ac0b2e31ccf62851 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69aa63804cd48190aef5e0f231600e58 |
completed | March 6, 2026, 5:17 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae892409f4819094ee3acc6942d1ee |
completed | March 9, 2026, 8:47 a.m. |
Created at: March 4, 2026, 7:30 p.m.