Triple
T37599695
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Silvermoon City |
E935489
|
entity |
| Predicate | previousPrimaryRace |
P201336
|
FINISHED |
| Object | high elves |
—
|
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: high elves | Statement: [Silvermoon City, previousPrimaryRace, high elves]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousPrimaryRace Context triple: [Silvermoon City, previousPrimaryRace, high elves]
-
A.
primaryRace
Indicates the main racial or ethnic category with which an entity is primarily identified or classified.
-
B.
primaryRaceType
Indicates the main or predominant race category associated with an entity, as opposed to any secondary or additional race classifications.
-
C.
racesPrimarilyIn
Indicates that an entity (such as a racer or racing team) mainly competes in a particular racing category, series, or environment.
-
D.
primaryNationality
Indicates the main national affiliation or citizenship that most strongly characterizes an entity among possibly multiple nationalities.
-
E.
relatedRace
Indicates that there is a connection or association between two races, such as similarity, relevance, or contextual linkage.
- F. None of above. chosen
Provenance (4 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_69f76ecf39c081909baffe597bb55273 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ffebbd9bac8190b3dca4b7252a2278 |
completed | May 10, 2026, 2:21 a.m. |
| PD | Predicate disambiguation | batch_69ffe93120a08190a44bb64d052eda78 |
completed | May 10, 2026, 2:10 a.m. |
| PDg | Predicate description generation | batch_69ffebbcef80819099714fa9b7fda762 |
completed | May 10, 2026, 2:21 a.m. |
Created at: May 3, 2026, 4:18 p.m.