Triple
T31485598
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SS-9 Scarp |
E803266
|
entity |
| Predicate | originatedFromProgram |
P17523
|
FINISHED |
| Object | Soviet R-36 missile program |
—
|
NE NERFINISHED |
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: Soviet R-36 missile program | Statement: [SS-9 Scarp, originatedFromProgram, Soviet R-36 missile program]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originatedFromProgram Context triple: [SS-9 Scarp, originatedFromProgram, Soviet R-36 missile program]
-
A.
originProgram
chosen
Indicates the program, initiative, or source project from which an entity, item, or record originally comes.
-
B.
originatesAs
Indicates that one entity begins, arises, or comes into existence in the form, state, or role specified by another entity.
-
C.
producedProgram
Indicates that one entity created or produced a specific program (such as a TV show, software, or other structured content).
-
D.
originalProgramLanguage
Indicates the programming language in which a program or software artifact was originally written.
-
E.
usedAsProgramFor
Indicates that one entity functions as the software or application used to operate, control, or provide services 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_69f348ca04508190ba9379b5329dfd75 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_6a00c9ddd62881909859a36b114a4132 |
completed | May 10, 2026, 6:09 p.m. |
| PD | Predicate disambiguation | batch_6a00c939b88881909d5353db4265e572 |
completed | May 10, 2026, 6:06 p.m. |
Created at: April 30, 2026, 9:35 p.m.