Triple
T16633416
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bob Mathias |
E404133
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Melba Mathias |
E404133
|
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: Melba Mathias | Statement: [Bob Mathias, spouse, Melba Mathias]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Melba Mathias Context triple: [Bob Mathias, spouse, Melba Mathias]
-
A.
Melba Mathias
chosen
Melba Mathias was the wife of American Olympic decathlon champion and politician Bob Mathias.
-
B.
Melba Phillips
Melba Phillips was an influential American physicist and educator known for her work in theoretical physics and for coauthoring the Oppenheimer–Phillips process in nuclear physics.
-
C.
Marlene Little
Marlene Little is known as the wife of Australian Aboriginal musician and entertainer Jimmy Little.
-
D.
Genevieve Mooy
Genevieve Mooy is an Australian actress known for her work in film, television, and theatre, including roles in productions such as "The Dish."
-
E.
Mary Tamm
Mary Tamm was a British actress best known for playing the first incarnation of the Time Lady Romana in the long-running science fiction series Doctor Who.
- 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_69d883897eb481909eaaa088ba9918d9 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e378e7d4a48190a9b4a14ecbb2a14b |
completed | April 18, 2026, 12:28 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a007dbe82b4819093b954567790bef7 |
completed | May 10, 2026, 12:44 p.m. |
Created at: April 10, 2026, 5:17 a.m.