Triple
T28203658
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | valley of the shadow of death |
E716955
|
entity |
| Predicate | hasHebrewTerm |
P6449
|
FINISHED |
| Object | גֵּיא צַלְמָוֶת (gei tsalmavet) |
—
|
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: גֵּיא צַלְמָוֶת (gei tsalmavet) | Statement: [valley of the shadow of death, hasHebrewTerm, גֵּיא צַלְמָוֶת (gei tsalmavet)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHebrewTerm Context triple: [valley of the shadow of death, hasHebrewTerm, גֵּיא צַלְמָוֶת (gei tsalmavet)]
-
A.
hasNameInHebrew
chosen
Indicates that an entity is associated with a specific name expressed in the Hebrew language.
-
B.
correspondsToInHebrew
Indicates that one entity is the Hebrew-language equivalent or counterpart of another entity.
-
C.
oftenRenderedFromHebrewTerm
Indicates that one term is frequently used as the translation or rendering of a corresponding term originating from Hebrew.
-
D.
hasKeyTermArabic
Indicates that an entity is associated with a specific key term expressed in the Arabic language.
-
E.
hasSingularHebrewForm
Indicates that an entity has a corresponding singular form in the Hebrew language.
- 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_69efd6b826908190857e6e7dad74ed93 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69f71996e1a48190ac59a1d66d7c44e8 |
completed | May 3, 2026, 9:47 a.m. |
| PD | Predicate disambiguation | batch_69f71820c6c88190ab38b4fa626d22cc |
completed | May 3, 2026, 9:40 a.m. |
Created at: April 27, 2026, 10:33 p.m.