Triple
T19663532
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | the Bottom |
E472142
|
entity |
| Predicate | appearsIn |
P795
|
FINISHED |
| Object | Sula |
—
|
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: Sula | Statement: [the Bottom, appearsIn, Sula]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sula Context triple: [the Bottom, appearsIn, Sula]
-
A.
Sula
chosen
Sula is a 1973 novel by American author Toni Morrison that explores Black female friendship, community, and identity in a small Ohio town.
-
B.
Sula
Sula is a coastal municipality in Møre og Romsdal county, Norway, known for its fishing industry, maritime heritage, and scenic island landscapes.
-
C.
Sula
Sula is a genus of large seabirds known as boobies, characterized by their strong diving ability and predominantly tropical oceanic distribution.
-
D.
Song of Solomon
Song of Solomon is a critically acclaimed novel by Toni Morrison that explores African American identity, family history, and the search for personal freedom through the life of its protagonist, Milkman Dead.
-
E.
Song of Solomon
Song of Solomon is a poetic book of the Old Testament that celebrates romantic love and intimacy through richly metaphorical dialogue between lovers.
- 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_69d8e514f2e08190ba70a4449519d218 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6416671fc81908e25b0477234fa0f |
completed | April 20, 2026, 3:08 p.m. |
Created at: April 10, 2026, 1:45 p.m.