Triple
T5037825
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sokar |
E113468
|
entity |
| Predicate | underworldRegion |
P60946
|
FINISHED |
| Object | realm of Sokar in the underworld |
—
|
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: realm of Sokar in the underworld | Statement: [Sokar, underworldRegion, realm of Sokar in the underworld]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: underworldRegion Context triple: [Sokar, underworldRegion, realm of Sokar in the underworld]
-
A.
subregionOf
Indicates that one region is geographically or administratively contained within, and is a part of, another larger region.
-
B.
worldRegion
Indicates that one entity is a geographic region that encompasses, contains, or is associated with the other entity within the world.
-
C.
region1
Indicates that one entity is the first or primary region associated with, containing, or encompassing another entity.
-
D.
originSubregion
Indicates the specific subregional area from which an entity originates or is derived.
-
E.
countrySubregion
Indicates that a country is located within or belongs to a specific subregion of the world.
- F. None of above. chosen
Provenance (4 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_69bd44384298819089c49e7c330ec7b8 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd73daaa788190b670f6c328bfa44f |
completed | March 20, 2026, 4:20 p.m. |
| PD | Predicate disambiguation | batch_69bd71529d608190a53470ba6c14bb1d |
completed | March 20, 2026, 4:09 p.m. |
| PDg | Predicate description generation | batch_69bd73617f348190b2fa68a0ef4fc7b1 |
completed | March 20, 2026, 4:18 p.m. |
Created at: March 20, 2026, 1:37 p.m.