Triple
T6362413
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Western astrology |
E143141
|
entity |
| Predicate | zodiacDivision |
P26315
|
FINISHED |
| Object | twelve equal 30-degree signs |
—
|
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: twelve equal 30-degree signs | Statement: [Western astrology, zodiacDivision, twelve equal 30-degree signs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: zodiacDivision Context triple: [Western astrology, zodiacDivision, twelve equal 30-degree signs]
-
A.
zodiacSystem
chosen
Indicates a relationship where an entity is associated with, defined by, or classified under a particular zodiac system or framework.
-
B.
positionInZodiac
Indicates the specific place or rank an entity occupies within the ordered sequence of zodiac signs.
-
C.
zodiacSpan
Indicates the range or period of dates during which a particular zodiac sign is considered to apply.
-
D.
zodiacRelation
Indicates a relationship between entities based on their positions or compatibility within the zodiac or astrological system.
-
E.
hasZodiacSignPart
Indicates that one entity is a component, segment, or subdivision of a zodiac sign represented by the other 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_69c008d7a9c4819098d647ec47776917 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c0680c02b481908618317566e31a5c |
completed | March 22, 2026, 10:07 p.m. |
| PD | Predicate disambiguation | batch_69c060ee055081908c79a1d151bd74cd |
completed | March 22, 2026, 9:36 p.m. |
Created at: March 22, 2026, 4:32 p.m.