Triple
T20949683
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Superman: Unbound |
E515944
|
entity |
| Predicate | voiceActor |
P1507
|
FINISHED |
| Object | Stana Katic |
—
|
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: Stana Katic | Statement: [Superman: Unbound, voiceActor, Stana Katic]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Stana Katic Context triple: [Superman: Unbound, voiceActor, Stana Katic]
-
A.
Stana Katic
chosen
Stana Katic is a Canadian-American actress best known for her role as Detective Kate Beckett on the television series "Castle."
-
B.
Vivien Visnjic
Vivien Visnjic is a child of Croatian-American actor Goran Visnjic, known for his role on the television series "ER."
-
C.
Lana Visnjic
Lana Visnjic is the daughter of Croatian actor Goran Visnjic.
-
D.
Tatiana Pajkovic
Tatiana Pajkovic is a Danish actress and musician known for her work in film and television and for her marriage to actor Boyd Holbrook.
-
E.
Marina Preko
Marina Preko is a small coastal marina and harbor facility located in the town of Preko on the island of Ugljan, Croatia, serving boaters and yachts in the Zadar area.
- 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_69e0b4fcd678819087a304291f14330a |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6fadc08148190b4ff710f94462a26 |
completed | April 21, 2026, 4:19 a.m. |
Created at: April 16, 2026, 1:18 p.m.