Triple
T9512726
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dominique Thorne as Riri Williams |
E229439
|
entity |
| Predicate | technologySpecialty |
P19268
|
FINISHED |
| Object | advanced armor design |
—
|
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: advanced armor design | Statement: [Dominique Thorne as Riri Williams, technologySpecialty, advanced armor design]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: technologySpecialty Context triple: [Dominique Thorne as Riri Williams, technologySpecialty, advanced armor design]
-
A.
technologyType
Indicates the specific kind or category of technology associated with an entity or relationship.
-
B.
technologyBasis
Indicates that one entity is founded on, enabled by, or fundamentally relies upon the technology provided or represented by another entity.
-
C.
technologyIncludes
Indicates that one technology encompasses, contains, or incorporates another technology as part of its components, features, or implementation.
-
D.
technologyField
chosen
Indicates the area or domain of technology in which an entity is involved, specialized, or categorized.
-
E.
technologyDiscussed
Indicates that a conversation, text, or interaction includes discussion or mention of a particular technology.
- 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_69ca84777560819084cddd999badc1aa |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd986aa99c8190b2eaa7f9b111aa2e |
completed | April 1, 2026, 10:12 p.m. |
| PD | Predicate disambiguation | batch_69cca567ca448190bf4bcce8ce7dd54f |
completed | April 1, 2026, 4:56 a.m. |
Created at: March 30, 2026, 7:58 p.m.