Triple
T10928031
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Viktor |
E258120
|
entity |
| Predicate | enemy |
P4567
|
FINISHED |
| Object | Lycans |
E717040
|
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: Lycans | Statement: [Viktor, enemy, Lycans]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lycans Context triple: [Viktor, enemy, Lycans]
-
A.
Lycans
chosen
Lycans are the werewolf-like, shape-shifting creatures central to the conflict in the Underworld film series.
-
B.
Vampires
"Vampires" is a song featured on the album *Nightlife*, likely reflecting its dark, nocturnal themes.
-
C.
Nightbreed
Nightbreed is a 1990 dark fantasy horror film written and directed by Clive Barker, adapted from his novella "Cabal," that explores a hidden underground city of monsters and outcasts.
-
D.
Night Creatures
"Night Creatures" is a late abstract expressionist painting by American artist Lee Krasner, reflecting her dynamic, gestural style and exploration of psychological intensity.
-
E.
Werewolf
"Werewolf" is a song by Fiona Apple from her critically acclaimed 2012 album *The Idler Wheel...*, noted for its raw emotional intensity and intricate lyricism.
- 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_69d6aa864ed88190818280ab6791d065 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7709da23c819096f4bba1cd4ff5cb |
completed | April 9, 2026, 9:25 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e217475344819088b44b6efb2df1c8 |
completed | April 17, 2026, 11:19 a.m. |
Created at: April 8, 2026, 9:22 p.m.