Triple
T23544213
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Desolation Island |
E577842
|
entity |
| Predicate | publisher |
P29
|
FINISHED |
| Object | Collins |
—
|
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: Collins | Statement: [Desolation Island, publisher, Collins]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Collins Context triple: [Desolation Island, publisher, Collins]
-
A.
Collins
chosen
Collins is a prominent British publishing brand best known for its dictionaries, atlases, and educational reference works.
-
B.
Collins
Collins is a common English-language surname borne by numerous notable individuals across fields such as politics, sports, literature, and entertainment.
-
C.
Collins
Collins is a major aerospace and defense technology company known for providing advanced avionics and aircraft systems to commercial and military customers worldwide.
-
D.
Collins
Collins is a small city located in Tattnall County in the southeastern part of the U.S. state of Georgia.
-
E.
Collins
Collins is a classic family of mixed drinks typically made with a base spirit, lemon juice, sugar, and carbonated water, served long over ice.
- 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_69e245f9d5d08190a4a20004e1784e20 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f1ae1ef55c8190a93c33e704ec3b5a |
completed | April 29, 2026, 7:07 a.m. |
Created at: April 17, 2026, 6:11 p.m.