Triple
T16906745
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Proto-Sinaitic letter ʿayin |
E424582
|
entity |
| Predicate | semanticValue |
P83565
|
FINISHED |
| Object | eye |
—
|
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: eye | Statement: [Proto-Sinaitic letter ʿayin, semanticValue, eye]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: semanticValue Context triple: [Proto-Sinaitic letter ʿayin, semanticValue, eye]
-
A.
semanticType
Indicates that something belongs to or is categorized under a particular semantic class or type based on its meaning.
-
B.
semanticRootMeaning
Indicates the fundamental or core meaning that underlies a word, phrase, or expression in a semantic structure.
-
C.
semanticsDetail
chosen
Indicates a more specific or fine-grained semantic characterization or nuance of a broader meaning or interpretation.
-
D.
valueExpressed
Indicates that a particular value, opinion, or quantitative measure is articulated, represented, or made explicit by an entity or expression.
-
E.
value
Indicates that one entity possesses, represents, or corresponds to a particular quantity, quality, or assigned worth.
- 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_69d889da3e8c8190a2b118f383f0beac |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e3ca39f9b08190b15106c6caf895ec |
completed | April 18, 2026, 6:15 p.m. |
| PD | Predicate disambiguation | batch_69e32b9489408190bcb2ede567ff5bf9 |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:30 a.m.