Triple
T17194724
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Uastyrdzhi festival |
E417317
|
entity |
| Predicate | honorsAspectOfUastyrdzhi |
P60804
|
FINISHED |
| Object | protector of the weak |
—
|
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: protector of the weak | Statement: [Uastyrdzhi festival, honorsAspectOfUastyrdzhi, protector of the weak]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: honorsAspectOfUastyrdzhi Context triple: [Uastyrdzhi festival, honorsAspectOfUastyrdzhi, protector of the weak]
-
A.
honorsAspectOf
chosen
Indicates that one entity shows respect, recognition, or reverence specifically toward a particular aspect, quality, or facet of another entity.
-
B.
honors
Indicates that one entity shows respect, recognition, or esteem toward another entity, often in a formal or ceremonial way.
-
C.
honourOf
Indicates that one entity is the source, bearer, or cause of another entity’s honor, prestige, or distinguished recognition.
-
D.
honoredThrough
Indicates that one entity is recognized or commemorated by means of another entity, event, or action.
-
E.
eraOfSignificance
Indicates the historical period or timeframe during which an entity was particularly important, influential, or noteworthy.
- 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_69d886d6ba8c819093215917b3d01689 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42da9e6208190b5c4e5925e840217 |
completed | April 19, 2026, 1:19 a.m. |
| PD | Predicate disambiguation | batch_69e383141ae0819096acd71683637cbc |
completed | April 18, 2026, 1:11 p.m. |
Created at: April 10, 2026, 5:38 a.m.