Triple
T19647917
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gifted |
E471728
|
entity |
| Predicate | character |
P662
|
FINISHED |
| Object |
Roberta Taylor
Roberta Taylor is a character in the television series "Gifted."
|
E1388810
|
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: Roberta Taylor | Statement: [Gifted, character, Roberta Taylor]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Roberta Taylor Context triple: [Gifted, character, Roberta Taylor]
-
A.
Elizabeth Scott
Elizabeth Scott was a Scottish noblewoman of the influential Scott family, daughter of Francis Scott, 2nd Earl of Buccleuch.
-
B.
Joan Sims
Joan Sims was a prolific English comedy actress best known for her roles in the "Carry On" film series and numerous British television and stage productions.
-
C.
Lara Bingle
Lara Bingle is an Australian model, media personality, and entrepreneur best known for her high-profile advertising campaigns and reality television appearances.
-
D.
Madge Dorita Walters
Madge Dorita Walters, better known as Madge Sinclair, was a Jamaican-born actress acclaimed for her roles in film and television, including "Roots," "Coming to America," and "Trapper John, M.D."
-
E.
Liz Robertson
Liz Robertson is a British musical theatre actress and singer known for her performances in West End and Broadway productions.
- 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: Roberta Taylor Triple: [Gifted, character, Roberta Taylor]
Generated description
Roberta Taylor is a character in the television series "Gifted."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Roberta Taylor Target entity description: Roberta Taylor is a character in the television series "Gifted."
-
A.
Elizabeth Scott
Elizabeth Scott was a Scottish noblewoman of the influential Scott family, daughter of Francis Scott, 2nd Earl of Buccleuch.
-
B.
Joan Sims
Joan Sims was a prolific English comedy actress best known for her roles in the "Carry On" film series and numerous British television and stage productions.
-
C.
Lara Bingle
Lara Bingle is an Australian model, media personality, and entrepreneur best known for her high-profile advertising campaigns and reality television appearances.
-
D.
Madge Dorita Walters
Madge Dorita Walters, better known as Madge Sinclair, was a Jamaican-born actress acclaimed for her roles in film and television, including "Roots," "Coming to America," and "Trapper John, M.D."
-
E.
Liz Robertson
Liz Robertson is a British musical theatre actress and singer known for her performances in West End and Broadway productions.
- 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_69d8e51395348190ac1416d46dfc6db0 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e64126cea88190a1a6929f46de4686 |
completed | April 20, 2026, 3:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a077eeced6881909429563193fd71d1 |
completed | May 15, 2026, 8:15 p.m. |
| NEDg | Description generation | batch_6a0783867f148190aaca0d1522689e3c |
completed | May 15, 2026, 8:35 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0784a7dba88190857275f577b5cc7c |
completed | May 15, 2026, 8:40 p.m. |
Created at: April 10, 2026, 1:44 p.m.