Triple
T20350778
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bears |
E495998
|
entity |
| Predicate | followedByWork |
P9710
|
FINISHED |
| Object | Monkey Kingdom |
—
|
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: Monkey Kingdom | Statement: [Bears, followedByWork, Monkey Kingdom]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Monkey Kingdom Context triple: [Bears, followedByWork, Monkey Kingdom]
-
A.
Monkey Kingdom
chosen
Monkey Kingdom is a nature documentary film directed by Alastair Fothergill that follows the lives and social dynamics of a troop of macaque monkeys in the jungles of Sri Lanka.
-
B.
Monkey Kingdom
Monkey Kingdom is a British television production company known for creating a range of popular entertainment and reality TV shows.
-
C.
Kensuke's Kingdom
Kensuke's Kingdom is a children's adventure novel by Michael Morpurgo about a boy stranded on a Pacific island who befriends a mysterious Japanese man living there.
-
D.
Skull Kingdom
Skull Kingdom is a sinister, likely supernatural realm or domain within the fantasy setting known as the Four Lands.
-
E.
Jungle of Nool
The Jungle of Nool is the lush, whimsical forest world in Dr. Seuss’s stories where Horton the elephant lives and discovers the tiny Whos.
- 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_69e0b4a3320881909495ae8bc30bc2dc |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6784f8ff48190a070888786f6a989 |
completed | April 20, 2026, 7:02 p.m. |
Created at: April 16, 2026, 11:24 a.m.