Triple
T16457039
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Superman Returns |
E399709
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Bryan Singer |
E259362
|
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: Bryan Singer | Statement: [Superman Returns, director, Bryan Singer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bryan Singer Context triple: [Superman Returns, director, Bryan Singer]
-
A.
Bryan Singer
chosen
Bryan Singer is an American film director and producer best known for helming several X-Men films and the crime thriller The Usual Suspects.
-
B.
Bruce Franklin Singer
Bruce Franklin Singer is a screenwriter best known for his work on the comedy film "Meatballs Part II."
-
C.
Sean Singer
Sean Singer is an American poet recognized for winning the prestigious Yale Series of Younger Poets prize.
-
D.
Josh Singer
Josh Singer is an American screenwriter known for his work on acclaimed films such as "Spotlight" and "The Post," often focusing on journalism and real-life events.
-
E.
Robert Singer
Robert Singer is a television producer and director best known for his long-running work on the fantasy-horror series "Supernatural."
- 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_69d87f2dac988190b74d6e185fa88ba4 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e32d7dfd188190b03e9b4151a4d3d8 |
completed | April 18, 2026, 7:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00607618c8819090fc9f18ae5f30dd |
completed | May 10, 2026, 10:39 a.m. |
Created at: April 10, 2026, 5:10 a.m.