Triple
T13353035
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gemini 2 |
E318115
|
entity |
| Predicate | testedSystems |
P109047
|
FINISHED |
| Object | guidance and control during reentry |
—
|
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: guidance and control during reentry | Statement: [Gemini 2, testedSystems, guidance and control during reentry]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: testedSystems Context triple: [Gemini 2, testedSystems, guidance and control during reentry]
-
A.
testedOn
Indicates that an entity has been used as the subject or material in a test, experiment, or evaluation performed by another entity.
-
B.
testedDevice
Indicates that one entity has performed a test on, or experimentally evaluated, another entity as a device.
-
C.
supportedSystem
Indicates that one entity provides compatibility, functionality, or operational support for another system.
-
D.
targetsSystems
Indicates that an entity is directed at, attacks, or is intended to affect specific systems.
-
E.
testedWith
Indicates that one entity has been examined, evaluated, or verified using another entity as the test method, tool, or counterpart.
- F. None of above. chosen
Provenance (4 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_69d806b5a3c08190b42c267fb092f98a |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d99e8d520881908aa23c7102b72b72 |
completed | April 11, 2026, 1:06 a.m. |
| PD | Predicate disambiguation | batch_69d98f6fd8bc819086dddb6f376efa57 |
completed | April 11, 2026, 12:01 a.m. |
| PDg | Predicate description generation | batch_69d9903fc2248190bd9894a45a2d0359 |
completed | April 11, 2026, 12:05 a.m. |
Created at: April 9, 2026, 9:32 p.m.