Triple
T13561735
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Virginia Fields |
E323923
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Michael Madden |
E337118
|
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: Michael Madden | Statement: [Virginia Fields, child, Michael Madden]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Madden Context triple: [Virginia Fields, child, Michael Madden]
-
A.
Michael Madden
chosen
Michael Madden is one of the sons of legendary American football coach and broadcaster John Madden.
-
B.
David Madden
David Madden is an American film and television producer and executive known for his work on acclaimed projects including the drama film "Places in the Heart."
-
C.
Michael McDonough
Michael McDonough is a cinematographer known for his work on independent and feature films, including the drama "Darling Companion."
-
D.
Michael McHugh
Michael McHugh is a former Justice of the High Court of Australia known for his influential contributions to Australian constitutional and common law jurisprudence.
-
E.
Richard McKenna
Richard McKenna was an American author and former U.S. Navy sailor best known for his novel "The Sand Pebbles," which drew on his naval experiences in China.
- 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_69d8076830b48190910a902bae5888e2 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbaff5219081909cf60423e79d278f |
completed | April 12, 2026, 2:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f76bb1ef508190ab587bd2aa34795b |
completed | May 3, 2026, 3:37 p.m. |
Created at: April 9, 2026, 9:47 p.m.