Triple
T20697551
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Krakoa |
E508695
|
entity |
| Predicate | language |
P15
|
FINISHED |
| Object | Krakoan |
—
|
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: Krakoan | Statement: [Krakoa, language, Krakoan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Krakoan Context triple: [Krakoa, language, Krakoan]
-
A.
Attilan
Attilan is the hidden, technologically advanced city-state that serves as the ancestral home of Marvel’s Inhumans.
-
B.
Krakoa
chosen
Krakoa is a living, sentient mutant island that serves as the sovereign homeland and central base for Marvel’s mutant population in the X-Men comics.
-
C.
Ossus
Ossus is a Jedi-inhabited world in the Star Wars Expanded Universe, known for its vast Jedi libraries and its devastation during ancient conflicts like the Great Sith War.
-
D.
Genosha
Genosha is a fictional island nation in Marvel Comics, notorious for its history of mutant enslavement, political upheaval, and catastrophic destruction.
-
E.
Taurision
Taurision is an ancient settlement in North Macedonia, traditionally identified as the birthplace of the Byzantine emperor Justinian I.
- 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_69e0b4c2b2a481909e31e9cb8f81ab55 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6c1132178819081086e085f7b3ff8 |
completed | April 21, 2026, 12:13 a.m. |
Created at: April 16, 2026, 12:11 p.m.