Triple
T12708455
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ann K. Curry |
E303649
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Brian Ross |
E990173
|
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: Brian Ross | Statement: [Ann K. Curry, spouse, Brian Ross]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brian Ross Context triple: [Ann K. Curry, spouse, Brian Ross]
-
A.
Brian Ross
chosen
Brian Ross is the husband of journalist and former NBC "Today" show co-anchor Ann Curry.
-
B.
Jim Doyle
Jim Doyle is an American Democratic politician who served as the 44th governor of Wisconsin from 2003 to 2011.
-
C.
Tom Marshall
Tom Marshall is a central character in the comedy adventure film "Without a Paddle," portrayed as a cautious and responsible friend who joins a chaotic river expedition in search of lost treasure.
-
D.
Joshua Hastert
Joshua Hastert is an American businessman and the son of former U.S. Speaker of the House Dennis Hastert.
-
E.
Jonathan Glickman
Jonathan Glickman is an American film producer known for overseeing a range of major Hollywood projects, including big-budget comedies and franchise films.
- 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_69d7bdef90d48190b46b88270e780946 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9620663e881908d367170ed6d2c81 |
completed | April 10, 2026, 8:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f671b648f48190a29924c484713fc7 |
completed | May 2, 2026, 9:50 p.m. |
Created at: April 9, 2026, 5:23 p.m.