Triple
T30711803
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Medusa |
E781913
|
entity |
| Predicate | legalityStatusInFiction |
P139339
|
FINISHED |
| Object | illegal |
—
|
LITERAL 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: illegal | Statement: [Medusa, legalityStatusInFiction, illegal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: legalityStatusInFiction Context triple: [Medusa, legalityStatusInFiction, illegal]
-
A.
rulesWithinFiction
Indicates that one set of rules governs or constrains events, characters, or elements within a fictional world or narrative.
-
B.
fictionalLaw
Indicates that a law, rule, or legal principle exists only within a fictional or imaginary context rather than in real-world legal systems.
-
C.
fictionalStatus
Indicates that an entity exists only in imagination or narrative and does not correspond to a real-world counterpart.
-
D.
legalStatusInUniverse
chosen
Indicates the formal legal standing or classification an entity holds within a specified fictional or conceptual universe.
-
E.
legalFiction
Indicates a relationship where something is treated as true or as having a particular legal status or effect, even though it is not literally or factually the case, for the purpose of applying or interpreting the law.
- F. None of above.
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_69f224acd24481908ed5f96f0d69b5dd |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fe5c1a502081909d4024e514309c8e |
completed | May 8, 2026, 9:56 p.m. |
| PD | Predicate disambiguation | batch_69fe5a9df21c819087153f5d0bcaa987 |
completed | May 8, 2026, 9:50 p.m. |
Created at: April 29, 2026, 8:35 p.m.