Triple
T20994860
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dana Reeve |
E517120
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Christopher Reeve |
—
|
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: Christopher Reeve | Statement: [Dana Reeve, spouse, Christopher Reeve]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Christopher Reeve Context triple: [Dana Reeve, spouse, Christopher Reeve]
-
A.
Christopher Reeve
chosen
Christopher Reeve was an American actor best known for his iconic portrayal of Superman in the late 1970s and 1980s film series.
-
B.
Will Reeve
Will Reeve is an American television journalist and the son of late actor Christopher Reeve and Dana Reeve.
-
C.
Reeve
Reeve is the given name of Reeve Lindbergh, an American author and the daughter of aviator Charles Lindbergh and writer Anne Morrow Lindbergh.
-
D.
Reeve
The Reeve is a shrewd, irritable estate manager and skilled carpenter who appears as one of the pilgrims and storytellers in Geoffrey Chaucer’s The Canterbury Tales.
-
E.
Reeve
A reeve is the elected head of the council in certain Canadian rural municipalities, functioning similarly to a mayor.
- 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_69e0b5006e2881909fc2383f841740cc |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fc1e75188190a97114238ea0b4f9 |
completed | April 21, 2026, 4:25 a.m. |
Created at: April 16, 2026, 1:50 p.m.