Triple
T19784039
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Updike |
E475211
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | The Centaur |
—
|
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 Centaur | Statement: [John Updike, notableWork, The Centaur]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: The Centaur Context triple: [John Updike, notableWork, The Centaur]
-
A.
The Centaur
chosen
The Centaur is a 1963 novel by John Updike that blends small-town American life with Greek mythology to explore themes of sacrifice, family, and human frailty.
-
B.
Centaur in Brass
"Centaur in Brass" is a short story by William Faulkner that continues the saga of the Snopes family in the fictional Yoknapatawpha County.
-
C.
Dying Centaur
Dying Centaur is a 19th-century allegorical sculpture by William Rimmer depicting a wounded mythological creature in a dramatic, expressive style.
-
D.
The Unicorn
The Unicorn is an American television sitcom that follows a widowed father navigating single parenthood and dating, known for its heartfelt humor and ensemble cast.
-
E.
The Unicorn
The Unicorn is an independent comedy film known for its offbeat exploration of modern relationships and commitment.
- 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_69d8e51b014081908b263e167370529a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65385ee8081908d58cc3ff05b9b23 |
completed | April 20, 2026, 4:25 p.m. |
Created at: April 10, 2026, 1:49 p.m.