Triple
T13792391
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cousin Skeeter |
E331429
|
entity |
| Predicate | portrayedBy |
P1507
|
FINISHED |
| Object | Skeeter |
E1064241
|
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: Skeeter | Statement: [Cousin Skeeter, portrayedBy, Skeeter]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Skeeter Context triple: [Cousin Skeeter, portrayedBy, Skeeter]
-
A.
Skeeter
Skeeter was the nickname of Skeeter Webb, an American Major League Baseball shortstop who played primarily in the 1940s.
-
B.
Skeeter
chosen
Skeeter is the wisecracking, puppet main character from the Nickelodeon live-action sitcom "Cousin Skeeter."
-
C.
Mozzie
Mozzie is a quirky, conspiracy-minded criminal mastermind and close ally of Neal Caffrey in the TV series "White Collar," known for his intelligence, paranoia, and offbeat humor.
-
D.
Avispa
Avispa is a Japanese professional football club based in Fukuoka that competes in the J1 League.
-
E.
Muscardin
Muscardin is a rare, light-colored red grape variety from France’s Rhône Valley, known for contributing floral aromas, high acidity, and finesse to Southern Rhône blends.
- 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_69d81c58feb08190a77bca8bf7d6d20f |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de0258a1408190a837d17c6d6a2bd4 |
completed | April 14, 2026, 9:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7c0e3642481908a9b84d8d71fb4d4 |
completed | May 3, 2026, 9:40 p.m. |
Created at: April 9, 2026, 10:11 p.m.