Triple
T3577902
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | XKeyscore |
E75730
|
entity |
| Predicate | relatedTo |
P37
|
FINISHED |
| Object | PRISM |
E75729
|
NE 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: PRISM | Statement: [XKeyscore, relatedTo, PRISM]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: PRISM Context triple: [XKeyscore, relatedTo, PRISM]
-
A.
PRISM
chosen
PRISM is a U.S. National Security Agency electronic surveillance program that collects and analyzes internet communications from major technology companies for intelligence and counterterrorism purposes.
-
B.
Prism
Prism is the 2013 pop studio album by American singer Katy Perry, featuring hits like "Roar" and "Dark Horse."
-
C.
Prismo
Prismo is a powerful wish-granting cosmic being from Adventure Time who exists outside normal time and space and influences major events across the multiverse.
-
D.
Prisma
Prisma is a modern TypeScript ORM and database toolkit that provides a type-safe and intuitive way to work with databases in Node.js applications.
-
E.
Prysm
Prysm is a widely used Ethereum consensus client implementation written in Go that helps manage validators and secure the network under proof-of-stake.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ad85d5e3008190bdfe0bacdd1f5a1b |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc0dd3e048190a0c6666e13ead9cd |
completed | March 8, 2026, 6:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b3bbc6bc948190a517639f5d79c0a3 |
completed | March 13, 2026, 7:24 a.m. |
Created at: March 8, 2026, 3:21 p.m.