Triple
T10311439
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elizabeth Perkins |
E241898
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Cats & Dogs |
E328386
|
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: Cats & Dogs | Statement: [Elizabeth Perkins, notableWork, Cats & Dogs]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cats & Dogs Context triple: [Elizabeth Perkins, notableWork, Cats & Dogs]
-
A.
Cats & Dogs
chosen
Cats & Dogs is a 2001 family action-comedy film that humorously depicts a secret high-tech war between rival cat and dog factions.
-
B.
Cats and Dogs
"Cats and Dogs" is a 1993 noise rock album by the American band Royal Trux, known for its lo-fi production and experimental, genre-blurring sound.
-
C.
CATS
CATS is the public transit agency serving the Charlotte, North Carolina metropolitan area, operating bus, light rail, and other transportation services.
-
D.
Catz
Catz is the informal nickname for St Catharine’s College, one of the constituent colleges of the University of Cambridge.
-
E.
Catz
Catz is the surname of Safra Catz, a prominent business executive best known as the CEO of Oracle Corporation.
- 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_69d381ac38808190a8ca7457c85b625b |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d32ac6c08190b23eb042b3ec284a |
completed | April 7, 2026, 9:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d71d78ece88190885768c979b038df |
completed | April 9, 2026, 3:31 a.m. |
Created at: April 6, 2026, 11:47 a.m.