Triple
T32797718
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kushite pantheon |
E838810
|
entity |
| Predicate | associatedWithMonumentType |
P25584
|
FINISHED |
| Object | pyramids of Kush |
—
|
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: pyramids of Kush | Statement: [Kushite pantheon, associatedWithMonumentType, pyramids of Kush]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedWithMonumentType Context triple: [Kushite pantheon, associatedWithMonumentType, pyramids of Kush]
-
A.
monumentType
chosen
Indicates the specific kind or category of monument that an entity is classified as.
-
B.
appliesToMonument
Indicates that something (such as a rule, status, or attribute) is relevant or applicable specifically to a monument.
-
C.
connectedToMonument
Indicates a relationship where something has a direct association, link, or relevance to a specific monument.
-
D.
associatedWithMuseum
Indicates a relationship where an entity has a formal or recognized connection to a museum, such as ownership, curation, exhibition, or institutional affiliation.
-
E.
monumentGroup
Indicates that one monument belongs to, or is categorized within, a specific group or collection of monuments.
- 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_69f3493c7f6881908edf2aa13631d1e0 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_6a037cad051c8190b28b354b89208574 |
completed | May 12, 2026, 7:17 p.m. |
| PD | Predicate disambiguation | batch_6a0379f0cbe481909b4b8fc6cbe297f0 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 1:14 a.m.