Triple
T14307768
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tyrosh |
E354740
|
entity |
| Predicate | ethnicMix |
P111672
|
FINISHED |
| Object | Valyrian descent |
—
|
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: Valyrian descent | Statement: [Tyrosh, ethnicMix, Valyrian descent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ethnicMix Context triple: [Tyrosh, ethnicMix, Valyrian descent]
-
A.
hasEthnicallyMixedPopulation
Indicates that a population is composed of people from multiple distinct ethnic groups rather than being ethnically homogeneous.
-
B.
ethnicComponents
chosen
Indicates that an entity is composed of, associated with, or characterized by one or more specified ethnic groups or ethnic origins.
-
C.
includesMixedSexRace
Indicates that the group or context involves individuals of more than one sex and more than one race.
-
D.
ethnicPluralityOf
Indicates that one ethnic group constitutes the largest share of the population within a given place or entity, though not necessarily an absolute majority.
-
E.
racialComposition
Indicates the proportional makeup of different racial groups within a given population or entity.
- 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_69d8278ed42c8190b9f882dcce611347 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de85b156b0819083f2bd319deed1b6 |
completed | April 14, 2026, 6:21 p.m. |
| PD | Predicate disambiguation | batch_69de2a8f81f08190af737e1654847aa6 |
completed | April 14, 2026, 11:52 a.m. |
Created at: April 10, 2026, 1:12 a.m.