Triple
T10657653
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Esther Harvey |
E251134
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Alfred Drake |
E29238
|
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: Alfred Drake | Statement: [Esther Harvey, spouse, Alfred Drake]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alfred Drake Context triple: [Esther Harvey, spouse, Alfred Drake]
-
A.
Alfred Drake
chosen
Alfred Drake was a prominent American actor and baritone best known for originating leading roles in landmark mid-20th-century Broadway musicals.
-
B.
Alfred Moss
Alfred Moss was a British amateur racing driver and dentist best known as the father of legendary Formula One driver Stirling Moss.
-
C.
Alfred Duckett
Alfred Duckett was an American writer and journalist best known for collaborating with Jackie Robinson on his autobiographical works.
-
D.
Alfred Jones
Alfred Jones is an individual known primarily by the formal title "Dr.," indicating that he holds a doctoral-level qualification or professional designation.
-
E.
George Fayne
George Fayne is a sporty, tomboyish friend and frequent sidekick of teen sleuth Nancy Drew in the long-running mystery book series.
- 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_69d6aa5a4c4881908f39be6efe5981e5 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6e0157dbc81909ef7d61f65b2fd93 |
completed | April 8, 2026, 11:09 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d98857ec248190bb655d36981a000a |
completed | April 10, 2026, 11:31 p.m. |
Created at: April 8, 2026, 9:07 p.m.