Triple
T16509759
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GBU-55 JDAM variant |
E401027
|
entity |
| Predicate | hasGuidance |
P488
|
FINISHED |
| Object | GPS/INS |
E26827
|
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: GPS/INS | Statement: [GBU-55 JDAM variant, hasGuidance, GPS/INS]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: GPS/INS Context triple: [GBU-55 JDAM variant, hasGuidance, GPS/INS]
-
A.
GPS
GPS is the Division of Geological and Planetary Sciences at the California Institute of Technology, focusing on research and education in Earth and planetary sciences.
-
B.
GPS
GPS is the three-letter National Rail station code for Great Portland Street station on the London Underground network.
-
C.
GPS
chosen
GPS (Global Positioning System) is a satellite-based navigation system that provides precise location and timing information to military and civilian users worldwide.
-
D.
GPS
GPS is a progressive rock/fusion band formed by former members of Asia, known for its virtuosic musicianship and complex compositions.
-
E.
GPS
GPS is an early artificial intelligence program developed in the late 1950s to model human problem-solving by systematically searching for solutions in a defined problem space.
- 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_69d88381f6148190819958a038be990e |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e32e54f7508190804bbae4c9bc8fe3 |
completed | April 18, 2026, 7:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a005833ef9c8190a2ff440942b83dc8 |
completed | May 10, 2026, 10:04 a.m. |
Created at: April 10, 2026, 5:14 a.m.