Triple
T12263135
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Megingjörð |
E292274
|
entity |
| Predicate | enhancesAttribute |
P39508
|
FINISHED |
| Object | Thor's already great strength |
—
|
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: Thor's already great strength | Statement: [Megingjörð, enhancesAttribute, Thor's already great strength]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: enhancesAttribute Context triple: [Megingjörð, enhancesAttribute, Thor's already great strength]
-
A.
enhancedBy
chosen
Indicates that one entity’s value, effectiveness, or impact is increased or improved as a result of another entity.
-
B.
usesAttribute
Indicates that one entity employs, relies on, or makes use of a specific attribute of another entity in performing an action or defining a relationship.
-
C.
attributesSuccessTo
Indicates that one entity regards another entity, factor, or action as the cause or source of a successful outcome.
-
D.
highlightsAttributeOf
Indicates that one entity draws attention to, emphasizes, or showcases a particular attribute or property of another entity.
-
E.
conveysAttribute
Indicates that one entity communicates, expresses, or imparts a particular attribute or quality to 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_69d6ab6856488190b5d31178d5015f8e |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d9380a5e78819086bd4dfe9a83d1f5 |
completed | April 10, 2026, 5:48 p.m. |
| PD | Predicate disambiguation | batch_69d91c4a66cc819083ce6fcaf5042af6 |
completed | April 10, 2026, 3:50 p.m. |
Created at: April 8, 2026, 9:52 p.m.