Triple
T37371637
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dimona reactor |
E927858
|
entity |
| Predicate | secrecyMeasures |
P13085
|
FINISHED |
| Object | restricted airspace |
—
|
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: restricted airspace | Statement: [Dimona reactor, secrecyMeasures, restricted airspace]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: secrecyMeasures Context triple: [Dimona reactor, secrecyMeasures, restricted airspace]
-
A.
secretes
Indicates that one entity produces and releases a substance from within itself into its surrounding environment or another entity.
-
B.
keepsSecretAbout
Indicates that one entity intentionally withholds or conceals information regarding another specified entity or topic from others.
-
C.
hasTypeOfSecrecy
chosen
Indicates that something is associated with a particular kind or level of secrecy.
-
D.
secretRevealed
Indicates that previously hidden or confidential information has been disclosed to one or more parties.
-
E.
protectionMeasures
Indicates actions or safeguards implemented to prevent harm, damage, or risk to someone or something.
- 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_69f76eb820248190a5c395ca50ad002a |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb8c38a9688190be524246f5682107 |
completed | May 6, 2026, 6:45 p.m. |
| PD | Predicate disambiguation | batch_69fb5a9c6e0481908565bd849e869b24 |
completed | May 6, 2026, 3:13 p.m. |
Created at: May 3, 2026, 4:16 p.m.