Triple
T14847446
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fabia Drake |
E349134
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Fabia Drake |
E349134
|
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: Fabia Drake | Statement: [Fabia Drake, name, Fabia Drake]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fabia Drake Context triple: [Fabia Drake, name, Fabia Drake]
-
A.
Fabia Drake
chosen
Fabia Drake was a British stage and film actress known for her long career in classical theatre and supporting roles in notable films.
-
B.
Francesca McFadden
Francesca McFadden is the wife of British Labour politician Pat McFadden.
-
C.
Chelsea Finn
Chelsea Finn is a prominent computer scientist and roboticist known for her influential research in meta-learning, reinforcement learning, and generalizable robot learning.
-
D.
Dahlia Travers
Dahlia Travers is a boisterous, warm-hearted, and strong-willed aunt of Bertie Wooster in P. G. Wodehouse’s Jeeves stories, known for her love of good food, gambling, and her magazine Milady’s Boudoir.
-
E.
Gabriela Dawson
Gabriela Dawson is a dedicated and compassionate paramedic and firefighter featured as a main character on the television drama series "Chicago Fire."
- 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_69d822ec69008190a9232caa68836872 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69ded29236dc8190b7d3a37d09f9fb21 |
completed | April 14, 2026, 11:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe72a87dd88190b0f0c3b9b625a7e6 |
completed | May 8, 2026, 11:32 p.m. |
Created at: April 10, 2026, 1:53 a.m.