Triple
T31516412
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Riri Williams |
E804083
|
entity |
| Predicate | armorPowerSource |
P8164
|
FINISHED |
| Object | repulsor-based technology |
—
|
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: repulsor-based technology | Statement: [Riri Williams, armorPowerSource, repulsor-based technology]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: armorPowerSource Context triple: [Riri Williams, armorPowerSource, repulsor-based technology]
-
A.
armorFeature
Indicates that one entity is a functional or descriptive feature of another entity’s armor.
-
B.
armorVariant
Indicates that one armor is a specific version, type, or modification derived from another armor.
-
C.
hasPowerSource
chosen
Indicates that an entity derives its operational energy or functionality from a specified power source.
-
D.
armorMaterial
Indicates that one entity serves as the material or substance from which another entity’s armor is made.
-
E.
sourceOfPower
Indicates that one entity serves as the origin or provider of power, energy, or authority for 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_69f348ceb0a48190ae7feca263b6296c |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6a25863648190867b5ad86681fee2 |
completed | May 3, 2026, 1:18 a.m. |
| PD | Predicate disambiguation | batch_69f69fe82e5c81909da9db0a2f3bba6d |
completed | May 3, 2026, 1:07 a.m. |
Created at: April 30, 2026, 9:53 p.m.