Triple
T8207029
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lady for a Day |
E191712
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | Ned Sparks |
E254367
|
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: Ned Sparks | Statement: [Lady for a Day, stars, Ned Sparks]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ned Sparks Context triple: [Lady for a Day, stars, Ned Sparks]
-
A.
Ned Sparks
chosen
Ned Sparks was a Canadian-born character actor best known for his deadpan expression and sarcastic, gravelly-voiced comedic roles in early Hollywood films.
-
B.
Sam Sneed
Sam Sneed is an American hip hop producer and rapper best known for his work with Death Row Records in the 1990s.
-
C.
Randy Sparks
Randy Sparks is an American musician, songwriter, and founder of the folk group The New Christy Minstrels, influential in the 1960s folk revival.
-
D.
Ned Graham
Ned Graham is an American Christian minister and the youngest son of evangelist Billy Graham and author Ruth Bell Graham.
-
E.
Ned Doyle
Ned Doyle was a businessman best known for owning the American Basketball Association team the Miami Floridians.
- 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_69ca82c7f3e08190857bf1fc63b2a10c |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb726b520081908ce4a03bd14dfcdf |
completed | March 31, 2026, 7:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ccedda69148190b8c221221de5dae5 |
completed | April 1, 2026, 10:05 a.m. |
Created at: March 30, 2026, 5:43 p.m.