Triple
T8977827
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hubertus |
E214439
|
entity |
| Predicate | meaningComponent_berht |
P16024
|
FINISHED |
| Object | bright |
—
|
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: bright | Statement: [Hubertus, meaningComponent_berht, bright]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: meaningComponent_berht Context triple: [Hubertus, meaningComponent_berht, bright]
-
A.
meaningComponent
chosen
Indicates that one entity represents a semantic or conceptual component contributing to the overall meaning of another entity.
-
B.
meaningComponent郎
Indicates that one entity is a semantic component or constituent part of the overall meaning of another entity.
-
C.
bentName
Indicates that an entity’s name is misspelled, malformed, or otherwise incorrectly rendered relative to its correct or standard form.
-
D.
HethIs
Indicates that one entity is identified as or equated with another entity, expressing a basic “is” or “being” relationship between them.
-
E.
boreTheBruntOf
Indicates that one entity received or endured the main force, impact, or negative consequences of an action or event caused by another 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_69ca839ea8b88190922c6a326ffcc0d3 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc67a33c8481909125acf4b7f0a919 |
completed | April 1, 2026, 12:32 a.m. |
| PD | Predicate disambiguation | batch_69cc5ed9a2d48190ad11381078e823b7 |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 7:02 p.m.