Triple
T20110871
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alexander Waugh |
E490324
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | Teresa Waugh |
—
|
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: Teresa Waugh | Statement: [Alexander Waugh, relative, Teresa Waugh]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Teresa Waugh Context triple: [Alexander Waugh, relative, Teresa Waugh]
-
A.
Teresa Waugh
chosen
Teresa Waugh is a British novelist and translator known for her works of fiction and for being part of the prominent Waugh literary family.
-
B.
Teresa Hill
Teresa Hill is an American actress best known for her television and film roles in the 1990s.
-
C.
Evelyn Bowen
Evelyn Bowen was an Irish actress and theatre director active in the early to mid-20th century, known for her work on stage in Ireland and Britain.
-
D.
Elizabeth Ayres
Elizabeth Ayres was the wife of American Revolutionary War officer and pioneering surveyor Rufus Putnam.
-
E.
Margaret Purvis
Margaret Purvis was the wife of famed FBI agent and crime-fighter Melvin Purvis, known for his role in the pursuit of notorious gangsters in the 1930s.
- 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_69da62636cc08190982cc71733a17b8d |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e666e0180c8190adeead0e60a099b0 |
completed | April 20, 2026, 5:48 p.m. |
Created at: April 11, 2026, 11:29 p.m.