Triple
T17810916
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jane Bingum |
E444700
|
entity |
| Predicate | friend |
P8712
|
FINISHED |
| Object | Stacy Barrett |
—
|
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: Stacy Barrett | Statement: [Jane Bingum, friend, Stacy Barrett]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Stacy Barrett Context triple: [Jane Bingum, friend, Stacy Barrett]
-
A.
Stacy Barrett
chosen
Stacy Barrett is a bubbly, loyal, and somewhat ditzy best friend character from the legal comedy-drama TV series "Drop Dead Diva."
-
B.
Stacey Shipman
Stacey Shipman is a central character in the British sitcom "Gavin & Stacey," known for her sweet, bubbly personality and long-distance romance with Gavin Shipman.
-
C.
Stacey Sutton
Stacey Sutton is a fictional geologist and Bond girl who appears as a key ally to James Bond in the 1985 film "A View to a Kill."
-
D.
Stacey Schroeder
Stacey Schroeder is a film editor best known for her work on the biographical comedy-drama "The Disaster Artist."
-
E.
Michelle Stacy
Michelle Stacy is an American former child voice actress best known for her roles in animated films of the 1970s and early 1980s.
- 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_69d8b9f0de78819099395b14db75a8a6 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4887b5e50819098506f0b92d709b5 |
completed | April 19, 2026, 7:47 a.m. |
Created at: April 10, 2026, 10:14 a.m.