Triple
T17719355
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Theresa Randle |
E442289
|
entity |
| Predicate | portrayed |
P1668
|
FINISHED |
| Object | Wanda Blake |
—
|
NE NERFINISHED |
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: Wanda Blake | Statement: [Theresa Randle, portrayed, Wanda Blake]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wanda Blake Context triple: [Theresa Randle, portrayed, Wanda Blake]
-
A.
Wanda Blake
chosen
Wanda Blake is a central character in the Spawn franchise, known as Al Simmons’ wife whose loss and later life without him drive much of his tragic, supernatural journey.
-
B.
Wanda
Wanda is one of the central protagonists in the country song "Goodbye Earl," known for conspiring with her friend Mary Ann to take revenge on her abusive husband.
-
C.
Wanda
Wanda is a feminine given name of Slavic origin, particularly common in Poland and other Central and Eastern European countries.
-
D.
Wanda
Wanda is a fairy godparent character from the animated series "The Fairly OddParents," known for her responsible and level-headed personality.
-
E.
Martha Coleman
Martha Coleman is a film producer known for her work on the British comedy-drama "Praise."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9ec79688190b86bdcef85a7b3aa |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e474844ff48190b1cf181eb9c113d9 |
completed | April 19, 2026, 6:21 a.m. |
Created at: April 10, 2026, 10:07 a.m.