Triple
T16191639
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | That's My Boy |
E392954
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Eva Amurri |
E282122
|
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: Eva Amurri | Statement: [That's My Boy, starring, Eva Amurri]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eva Amurri Context triple: [That's My Boy, starring, Eva Amurri]
-
A.
Eva Amurri
chosen
Eva Amurri is an American actress and lifestyle blogger known for her film and television roles as well as being the daughter of actress Susan Sarandon and director Franco Amurri.
-
B.
Eva Riccobono
Eva Riccobono is an Italian model and actress known for her work in fashion and film.
-
C.
Eleonora Vallone
Eleonora Vallone is an Italian actress and former model known for her film and television work in the late 20th century.
-
D.
Elena Benedetti
Elena Benedetti is a central fictional character in Pedro Almodóvar’s film "Live Flesh," around whom much of the drama and emotional conflict revolves.
-
E.
Marcella De Marchis
Marcella De Marchis was an Italian costume and production designer active in mid-20th-century cinema and theater.
- 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_69d87f1e49ac8190a311b54d32990576 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e222d5769c8190bbb604bfa095a1a5 |
completed | April 17, 2026, 12:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0017a7223c81909f04144bdffb22ff |
completed | May 10, 2026, 5:29 a.m. |
Created at: April 10, 2026, 5:02 a.m.