Triple
T21428465
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Finding Fanny |
E528621
|
entity |
| Predicate | character |
P662
|
FINISHED |
| Object |
Savvy
Savvy is a supporting character in the Indian film "Finding Fanny," contributing to the quirky ensemble in this offbeat Goan road-trip story.
|
E1484134
|
NE FINISHED |
How this triple was built (4 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: Savvy | Statement: [Finding Fanny, character, Savvy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Savvy Context triple: [Finding Fanny, character, Savvy]
-
A.
Kluge
Kluge is a German surname borne by several notable figures, including military leaders, scholars, and public personalities.
-
B.
Pretty Smart
Pretty Smart is a Netflix comedy series following a high-strung, intellectual woman who moves in with her carefree sister and her quirky roommates, starring Emily Osment.
-
C.
Get Smart
Get Smart is a 2008 action-comedy film adaptation of the classic TV series, starring Steve Carell as an inept secret agent alongside Anne Hathaway.
-
D.
Smart Ass
Smart Ass is a popular medium-roast coffee blend by Kicking Horse Coffee known for its bright, sweet, and chocolaty flavor profile.
-
E.
Wise Up
Wise Up is a Brazilian language school franchise best known for its intensive English courses aimed at adults and professionals.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Savvy Triple: [Finding Fanny, character, Savvy]
Generated description
Savvy is a supporting character in the Indian film "Finding Fanny," contributing to the quirky ensemble in this offbeat Goan road-trip story.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Savvy Target entity description: Savvy is a supporting character in the Indian film "Finding Fanny," contributing to the quirky ensemble in this offbeat Goan road-trip story.
-
A.
Kluge
Kluge is a German surname borne by several notable figures, including military leaders, scholars, and public personalities.
-
B.
Pretty Smart
Pretty Smart is a Netflix comedy series following a high-strung, intellectual woman who moves in with her carefree sister and her quirky roommates, starring Emily Osment.
-
C.
Get Smart
Get Smart is a 2008 action-comedy film adaptation of the classic TV series, starring Steve Carell as an inept secret agent alongside Anne Hathaway.
-
D.
Smart Ass
Smart Ass is a popular medium-roast coffee blend by Kicking Horse Coffee known for its bright, sweet, and chocolaty flavor profile.
-
E.
Wise Up
Wise Up is a Brazilian language school franchise best known for its intensive English courses aimed at adults and professionals.
- F. None of above. chosen
Provenance (5 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_69e0c455f3688190810bc96365791b0f |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e8b3e74bcc81909ad66e3c59152ffc |
completed | April 22, 2026, 11:41 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a09c2aa56b081909ddfc07b7b5fd60e |
completed | May 17, 2026, 1:29 p.m. |
| NEDg | Description generation | batch_6a09c3a036408190a759223303268183 |
completed | May 17, 2026, 1:33 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a09c49aa5b881908ac2e920684a9fa2 |
completed | May 17, 2026, 1:37 p.m. |
Created at: April 16, 2026, 5:49 p.m.