Triple
T17212181
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Macho Man Randy Savage |
E417758
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Miss Elizabeth |
E1234435
|
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: Miss Elizabeth | Statement: [Macho Man Randy Savage, spouse, Miss Elizabeth]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Miss Elizabeth Context triple: [Macho Man Randy Savage, spouse, Miss Elizabeth]
-
A.
Miss Elizabeth
chosen
Miss Elizabeth was a prominent professional wrestling valet and manager best known for her iconic role alongside "Macho Man" Randy Savage in the WWF during the 1980s and early 1990s.
-
B.
Miss Jane
Miss Jane is the former stage name of Ghanaian singer and songwriter Efya, known for her soulful Afrobeat and neo-soul music.
-
C.
Miss Andrew
Miss Andrew is a strict, authoritarian nanny character who appears as a foil to Mary Poppins in adaptations of the Mary Poppins stories.
-
D.
Miss Stewart
Miss Stewart was an educator significant enough in San Rafael, California, that a local school was named in her honor.
-
E.
Lizzie
Lizzie is a common English feminine given name, often used as a diminutive of names like Elizabeth or Liza.
- 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_69d886d779488190b131369541c04e7d |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42dc68a2c81908564231853b40db9 |
completed | April 19, 2026, 1:20 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a01674fadc48190aa4a627ec9f72341 |
completed | May 11, 2026, 5:21 a.m. |
Created at: April 10, 2026, 5:38 a.m.