Triple
T16457051
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Superman Returns |
E399709
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Brandon Routh |
E576009
|
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: Brandon Routh | Statement: [Superman Returns, starring, Brandon Routh]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brandon Routh Context triple: [Superman Returns, starring, Brandon Routh]
-
A.
Brandon Routh
chosen
Brandon Routh is an American actor best known for portraying Superman/Clark Kent in the 2006 film "Superman Returns."
-
B.
Chris Swanson
Chris Swanson is a music industry executive and co-founder of the independent record label Dead Oceans, known for its roster of acclaimed indie and alternative artists.
-
C.
Hugh Brooke
Hugh Brooke was a mid-20th-century screenwriter known for his work on British and American films, including the 1951 drama "Journey into Light."
-
D.
Rob Morrow
Rob Morrow is an American actor best known for his roles in the television series "Northern Exposure" and "Numb3rs."
-
E.
Casper Van Dien
Casper Van Dien is an American actor best known for his leading role as Johnny Rico in the science fiction film "Starship Troopers."
- 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_6a004f5015a881908447b64b699feb1a |
completed | May 10, 2026, 9:26 a.m. |
Created at: April 10, 2026, 5:10 a.m.