Triple
T13286830
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Abiel Abbot Low |
E316465
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Ellen Almira Dow |
E340078
|
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: Ellen Almira Dow | Statement: [Abiel Abbot Low, spouse, Ellen Almira Dow]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ellen Almira Dow Context triple: [Abiel Abbot Low, spouse, Ellen Almira Dow]
-
A.
Ellen Almira Low
chosen
Ellen Almira Low was an individual belonging to the historically notable Low family lineage.
-
B.
Ellen Evangeline Hovick
Ellen Evangeline Hovick is the birth name of June Havoc, an American actress, dancer, and stage director known for her work in vaudeville, film, and theater.
-
C.
Ellen Agnus Pitt
Ellen Agnus Pitt was the mother of the influential English illustrator and author Aubrey Beardsley.
-
D.
Emily Augusta Andrews
Emily Augusta Andrews was the first wife of Victorian poet Coventry Patmore and the inspiration for his famous poetic sequence "The Angel in the House."
-
E.
Lydia Hurlbut
Lydia Hurlbut is an American entrepreneur and co-founder/CEO of the Hurlbut Academy, an educational platform for filmmakers that she runs with her husband, cinematographer Shane Hurlbut.
- 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_69d806b349908190a9a61dd9323bf153 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d990759ebc8190a9487a59e37a69e2 |
completed | April 11, 2026, 12:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f77f7846008190aa27fafe19056807 |
completed | May 3, 2026, 5:01 p.m. |
Created at: April 9, 2026, 9:27 p.m.