Triple
T21505057
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | On Kawara |
E530575
|
entity |
| Predicate | hasSeries |
P1761
|
FINISHED |
| Object | One Million Years |
—
|
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: One Million Years | Statement: [On Kawara, hasSeries, One Million Years]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: One Million Years Context triple: [On Kawara, hasSeries, One Million Years]
-
A.
One Million Years
chosen
One Million Years is a conceptual art project by On Kawara consisting of meticulously typed volumes listing every year over a vast temporal span, reflecting on time, existence, and human mortality.
-
B.
Million Years Ago
"Million Years Ago" is a melancholic, acoustic ballad by Adele reflecting on nostalgia and lost time, featured on her album "25."
-
C.
Billion Year Spree
Billion Year Spree is a critical history of science fiction by Brian W. Aldiss that traces the genre’s development from its early roots to the modern era.
-
D.
A Billion
"A Billion" is a song featured on the soundtrack of the musical film "The King & I."
-
E.
4 Billion Souls
"4 Billion Souls" is a song by the British rock band Full Circle.
- 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_69e0c45c81f08190a6b8bbb70a45aae7 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea7cb5588190a4473bbfe3f49cbb |
completed | April 23, 2026, 9:46 a.m. |
Created at: April 16, 2026, 6:24 p.m.