Triple
T19162296
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thoth Tarot |
E469084
|
entity |
| Predicate | hasCorrespondence |
P106119
|
FINISHED |
| Object | Hebrew letters |
—
|
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: Hebrew letters | Statement: [Thoth Tarot, hasCorrespondence, Hebrew letters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCorrespondence Context triple: [Thoth Tarot, hasCorrespondence, Hebrew letters]
-
A.
hasCorrespondenceForm
Indicates that there exists a specific format, template, or structural representation used for the correspondence associated with an entity.
-
B.
containsCorrespondenceWith
Indicates that one entity includes or holds correspondence (such as messages or communications) that is associated with or exchanged with another entity.
-
C.
correspondsWith
chosen
Indicates that two entities are in mutual alignment or agreement, such that one matches, parallels, or is equivalent to the other in a specified respect.
-
D.
hasCorrespondingAuthor
Indicates that an entity (such as a publication) is linked to the author who serves as the primary contact responsible for correspondence about it.
-
E.
correspondedWith
Indicates that two entities engaged in mutual communication, typically by exchanging messages or letters over a period of time.
- 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_69d8dd084ff48190ac0f8c46ee722629 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5eebe03ac8190bbe0b34ebf0d90c6 |
completed | April 20, 2026, 9:15 a.m. |
| PD | Predicate disambiguation | batch_69e4b9b83d6881908e6271c620f74100 |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 12:06 p.m.