Triple
T26061193
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mukarrib |
E657266
|
entity |
| Predicate | combinesFunctionsOf |
P108317
|
FINISHED |
| Object | high priest |
—
|
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: high priest | Statement: [Mukarrib, combinesFunctionsOf, high priest]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: combinesFunctionsOf Context triple: [Mukarrib, combinesFunctionsOf, high priest]
-
A.
combinesFeaturesOf
Indicates that one entity integrates or merges characteristics, attributes, or functionalities originating from multiple other entities.
-
B.
combinedFunction
Indicates that multiple functions or operations are brought together and applied as a single, unified function or process.
-
C.
combinesRoleOf
chosen
Indicates a relationship where a single entity simultaneously fulfills or merges multiple distinct roles or functions.
-
D.
combinesPowers
Indicates that two or more entities merge their abilities or strengths to produce a unified, often enhanced, effect.
-
E.
knownForCombining
Indicates a relationship where one entity is recognized or notable for bringing together or merging multiple elements, entities, or aspects into a unified whole.
- 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_69ee5bbd788481909e22bd7153d0c037 |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69f60692a4f081909cd9d0ca75d590a0 |
completed | May 2, 2026, 2:13 p.m. |
| PD | Predicate disambiguation | batch_69f5f7fba5248190945acf1561280799 |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 26, 2026, 7:17 p.m.