Triple
T8229610
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Linear B |
E192255
|
entity |
| Predicate | deciphermentMethod |
P14388
|
FINISHED |
| Object | structural analysis and comparison with Greek |
—
|
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: structural analysis and comparison with Greek | Statement: [Linear B, deciphermentMethod, structural analysis and comparison with Greek]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: deciphermentMethod Context triple: [Linear B, deciphermentMethod, structural analysis and comparison with Greek]
-
A.
deciphermentContributor
Indicates that an entity contributed to the process of deciphering or interpreting another entity (such as a text, code, or inscription).
-
B.
deciphermentStatus
Indicates the degree to which something (such as a text, code, or inscription) has been successfully decoded or interpreted.
-
C.
deciphermentDate
Indicates the date on which something (such as a text, code, or inscription) was successfully deciphered or decoded.
-
D.
decodingMethod
chosen
Indicates the technique or process used to convert encoded or encrypted data back into its original, interpretable form.
-
E.
deciphermentPeriod
Indicates the time span during which the decipherment of something (such as a script, code, or text) took place.
- 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_69ca82db5b90819085d1ad7c2e27bfcc |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb7802417c81908837c31136c41a5c |
completed | March 31, 2026, 7:30 a.m. |
| PD | Predicate disambiguation | batch_69cb36b1dea0819091418072501e79c1 |
completed | March 31, 2026, 2:51 a.m. |
Created at: March 30, 2026, 5:46 p.m.