Triple
T18574327
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Snowden leaks |
E453947
|
entity |
| Predicate | revealedProgram |
P38401
|
FINISHED |
| Object | MUSCULAR |
—
|
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: MUSCULAR | Statement: [Snowden leaks, revealedProgram, MUSCULAR]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MUSCULAR Context triple: [Snowden leaks, revealedProgram, MUSCULAR]
-
A.
MUSCULAR
chosen
MUSCULAR is a formerly secret joint NSA–GCHQ surveillance program that tapped into private data links between major tech companies’ data centers to collect large volumes of user information.
-
B.
De musculis
De musculis is an anatomical treatise by Renaissance surgeon and anatomist Hieronymus Fabricius that focuses on the structure and function of muscles.
-
C.
Blood Muscle Skin & Bone
Blood Muscle Skin & Bone is a track from Brandi Carlile’s album "The Firewatcher’s Daughter," showcasing her emotive vocals and introspective songwriting.
-
D.
Relaxed Muscle
Relaxed Muscle is an experimental electro-rock side project fronted by Pulp singer Jarvis Cocker under a pseudonym.
-
E.
Mr Muscle
Mr Muscle is a household cleaning product brand known for its range of powerful cleaners for kitchens, bathrooms, and other hard surfaces.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8d38974308190a9174430ef256b73 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e543c8c0608190afc99235006bf87f |
completed | April 19, 2026, 9:06 p.m. |
Created at: April 10, 2026, 11:43 a.m.