Triple
T37305229
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Naxos |
E926060
|
entity |
| Predicate | racialCompositionInFiction |
P176827
|
FINISHED |
| Object | predominantly Black |
—
|
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: predominantly Black | Statement: [Naxos, racialCompositionInFiction, predominantly Black]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: racialCompositionInFiction Context triple: [Naxos, racialCompositionInFiction, predominantly Black]
-
A.
hasEthnicityInFiction
Indicates that a fictional character or entity is portrayed as having a particular ethnicity within a narrative or fictional context.
-
B.
audienceCompositionInFiction
Indicates the relationship between a fictional work and the makeup or characteristics of the audience depicted within that fictional context.
-
C.
fictionalEthnicFocus
Indicates that something is primarily concerned with, centered on, or thematically emphasizes a fictional or invented ethnic group.
-
D.
raceWithinFiction
chosen
Indicates that one fictional character or entity belongs to a particular race or species within a fictional universe.
-
E.
hasFictionalDemographic
Indicates that an entity is associated with a demographic group that is fictional or exists only within a created narrative or imagined context.
- 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_69f76eb1bc508190924e9fa5d8acdeb3 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb9e1845e881908d19158440cf3b87 |
completed | May 6, 2026, 8:01 p.m. |
| PD | Predicate disambiguation | batch_69fb8d08d6988190a00794ac26078348 |
completed | May 6, 2026, 6:48 p.m. |
Created at: May 3, 2026, 4:16 p.m.