Triple
T19331231
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frances Tomelty |
E483498
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Frances Tomelty |
E483498
|
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: Frances Tomelty | Statement: [Frances Tomelty, name, Frances Tomelty]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Frances Tomelty Context triple: [Frances Tomelty, name, Frances Tomelty]
-
A.
Frances Tomelty
chosen
Frances Tomelty is a Northern Irish actress known for her work in television, film, and theatre, and for her former marriage to musician Sting.
-
B.
Mary Jean Tomlin
Mary Jean Tomlin, better known as Lily Tomlin, is an acclaimed American actress, comedian, writer, and producer renowned for her work in television, film, and theater since the 1960s.
-
C.
Eileen Shearer
Eileen Shearer is a political figure best known for founding the American Independent Party in the United States.
-
D.
Joan Tompkins
Joan Tompkins was an American character actress known for her work in mid-20th-century film and television.
-
E.
Kathleen Glynn
Kathleen Glynn is an American film producer and television creator best known for her long-time professional and personal collaboration with documentary filmmaker Michael Moore.
- 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_69d8e8d13e3c81909d91d1d5ec37c095 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e616422fa08190bf4bde4312ec7cf3 |
completed | April 20, 2026, 12:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a07ccb1ef608190af8bd4e7cd8c63cf |
completed | May 16, 2026, 1:47 a.m. |
Created at: April 10, 2026, 1:33 p.m.