Triple
T37514040
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | King Rakkis |
E932587
|
entity |
| Predicate | raceInUniverse |
P111399
|
FINISHED |
| Object | human (Sanctuary) |
—
|
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: human (Sanctuary) | Statement: [King Rakkis, raceInUniverse, human (Sanctuary)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: raceInUniverse Context triple: [King Rakkis, raceInUniverse, human (Sanctuary)]
-
A.
ethnicityInUniverse
chosen
Indicates that, within a given fictional or defined universe, a particular entity is associated with or belongs to a specified ethnicity as understood in that universe.
-
B.
eraInUniverse
Indicates the specific time period or era during which something exists or occurs within a particular fictional or defined universe.
-
C.
relatedRace
Indicates that there is a connection or association between two races, such as similarity, relevance, or contextual linkage.
-
D.
hasInUniverseInhabitants
Indicates that a universe or fictional setting contains certain beings or populations as its inhabitants.
-
E.
continentOfRaces
Indicates the continent on which a given race or set of races takes place or is primarily located.
- 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_69f76ec730988190b5aa4f9cb9afd518 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fba5eec0448190a5e6f0c43fdcd0e3 |
completed | May 6, 2026, 8:34 p.m. |
| PD | Predicate disambiguation | batch_69fba34edd548190bfa980e6e16e0a88 |
completed | May 6, 2026, 8:23 p.m. |
Created at: May 3, 2026, 4:17 p.m.