Triple
T23023228
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Over Her Dead Body |
E573225
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Eva Longoria |
—
|
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: Eva Longoria | Statement: [Over Her Dead Body, starring, Eva Longoria]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eva Longoria Context triple: [Over Her Dead Body, starring, Eva Longoria]
-
A.
Eva Longoria
chosen
Eva Longoria is an American actress, producer, and entrepreneur best known for her role on the television series "Desperate Housewives."
-
B.
Eiza González
Eiza González is a Mexican actress and singer known for her roles in films such as "Baby Driver," "Alita: Battle Angel," and "Welcome to Marwen," as well as the TV series "From Dusk Till Dawn: The Series."
-
C.
Sophia Garcia-Frizzi
Sophia Garcia-Frizzi is an actress best known for playing Judith Grimes on the television series "The Walking Dead."
-
D.
Eva Mendes
Eva Mendes is an American actress and model known for her roles in films such as "Training Day," "Hitch," and "The Place Beyond the Pines."
-
E.
Erika Buenfil
Erika Buenfil is a Mexican actress and television personality best known for her leading roles in popular telenovelas.
- 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_69e245b821008190b0e09cb02092aae1 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f183ea23088190b2f42d9bf01514ac |
completed | April 29, 2026, 4:07 a.m. |
Created at: April 17, 2026, 3:52 p.m.