Triple
T13992642
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prima Facie |
E336618
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | Suzie Miller |
E1189386
|
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: Suzie Miller | Statement: [Prima Facie, writer, Suzie Miller]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Suzie Miller Context triple: [Prima Facie, writer, Suzie Miller]
-
A.
Suzie Miller
chosen
Suzie Miller is an Australian playwright, screenwriter, and former human rights lawyer best known for her acclaimed one-woman play "Prima Facie."
-
B.
Suzy Miller
Suzy Miller is a former British model and socialite best known for her high-profile marriages to Formula One driver James Hunt and later actor Richard Burton.
-
C.
Tamara Miller
Tamara Miller is a member of the Disney family and a granddaughter of Walt Disney through his daughter Diane Disney Miller.
-
D.
Suzanne Smith
Suzanne Smith is known as the spouse of Irish actor Dermot Crowley.
-
E.
Suzanne Johnson
Suzanne Johnson is a member of the Johnson family, known primarily in relation to that family group.
- 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_69d81c639e808190a0e4b4f3d31c6a59 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2eb3b5d881909f15a1e08bb202f3 |
completed | April 14, 2026, 12:10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffe46175b88190ae687073ddaa3d22 |
completed | May 10, 2026, 1:50 a.m. |
Created at: April 9, 2026, 10:19 p.m.