Triple
T12385737
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Geoffrey Unsworth |
E295858
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Zardoz |
E386238
|
NE FINISHED |
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: Zardoz | Statement: [Geoffrey Unsworth, notableWork, Zardoz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zardoz Context triple: [Geoffrey Unsworth, notableWork, Zardoz]
-
A.
Zardoz
chosen
Zardoz is a 1974 science fiction film directed by John Boorman, known for its surreal, dystopian vision and starring Sean Connery in one of his most unconventional roles.
-
B.
Zaar
Zaar is a West Chadic language spoken primarily in Bauchi State, Nigeria.
-
C.
Yantzaza
Yantzaza is a town in southeastern Ecuador that serves as an administrative and commercial center in the Zamora-Chinchipe Province.
-
D.
Zezuru
Zezuru is a major dialect of the Shona language spoken primarily in central and northern Zimbabwe.
-
E.
Zarda
Zarda is a landmark U.S. Supreme Court case that held federal law prohibits employment discrimination based on sexual orientation.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d6ad9e653c8190b1473c860ee53dae |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d93fbd489c819098233a111442762e |
completed | April 10, 2026, 6:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f62ac939bc819081629b9eef20c4e7 |
completed | May 2, 2026, 4:48 p.m. |
Created at: April 8, 2026, 9:54 p.m.