Triple
T17906547
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kevin |
E447715
|
entity |
| Predicate | dislikes |
P62730
|
FINISHED |
| Object | the Eds |
—
|
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: the Eds | Statement: [Kevin, dislikes, the Eds]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: the Eds Context triple: [Kevin, dislikes, the Eds]
-
A.
the Eds
chosen
The Eds are the central trio of misfit boys in the animated series "Ed, Edd n Eddy," known for their elaborate money-making schemes and slapstick misadventures in the cul-de-sac.
-
B.
EDY
EDY is the National Rail station code for East Didsbury railway station in Manchester, England.
-
C.
Dix & Edwards
Dix & Edwards was a 19th-century American publishing firm known for issuing literary works, including notable pieces by authors such as Herman Melville.
-
D.
"Ed"
"Ed" is an early-2000s American dramedy TV series about a lawyer who returns to his hometown to run a bowling alley while practicing law, starring Tom Cavanagh in the title role.
-
E.
Edis
Edis is a surname most notably associated with the English architect Robert William Edis, known for his contributions to Victorian-era architecture and interior design.
- 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_69d8b9f6d394819082a6d69fd1e23d2f |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49e9c7f54819088c6d2ce7bbea073 |
completed | April 19, 2026, 9:21 a.m. |
Created at: April 10, 2026, 10:19 a.m.