Triple
T36283084
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zoba |
E892992
|
entity |
| Predicate | regionOfPresence |
P86016
|
FINISHED |
| Object | Arabian Peninsula and surrounding regions |
—
|
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: Arabian Peninsula and surrounding regions | Statement: [Zoba, regionOfPresence, Arabian Peninsula and surrounding regions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regionOfPresence Context triple: [Zoba, regionOfPresence, Arabian Peninsula and surrounding regions]
-
A.
regionOfAssociation
chosen
Indicates a broader geographic or spatial area with which an entity is functionally, contextually, or organizationally associated.
-
B.
registrationRegion
Indicates the geographic or administrative region in which an entity is officially registered.
-
C.
regionOfRecognition
Indicates the geographic or administrative area within which something is officially acknowledged, valid, or recognized.
-
D.
regionFrom
Indicates that something originates from, is derived from, or is associated with a particular geographic or administrative region.
-
E.
regionOfHostCountry
Indicates that one entity is a geographic or administrative region belonging to, or located within, the specified host country.
- 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_69f76e4955c08190b8cfddca34fc0242 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a00119d821c8190874786391b27ef23 |
completed | May 10, 2026, 5:03 a.m. |
| PD | Predicate disambiguation | batch_6a001143fb6881909ac0ae8bfea04351 |
completed | May 10, 2026, 5:01 a.m. |
Created at: May 3, 2026, 4:09 p.m.