Triple
T31584536
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Atropatene |
E805919
|
entity |
| Predicate | regionNamePreservedIn |
P197417
|
FINISHED |
| Object |
Middle Persian Adurbadagan
Middle Persian Adurbadagan was the Sasanian-era province in northwestern Iran that preserved the name and territory of the earlier region of Atropatene.
|
E1969514
|
NE FINISHED |
How this triple was built (3 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: Middle Persian Adurbadagan | Statement: [Atropatene, regionNamePreservedIn, Middle Persian Adurbadagan]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Middle Persian Adurbadagan Triple: [Atropatene, regionNamePreservedIn, Middle Persian Adurbadagan]
Generated description
Middle Persian Adurbadagan was the Sasanian-era province in northwestern Iran that preserved the name and territory of the earlier region of Atropatene.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regionNamePreservedIn Context triple: [Atropatene, regionNamePreservedIn, Middle Persian Adurbadagan]
-
A.
regionName
Indicates the name assigned to a specific geographic or administrative region.
-
B.
regionNameUsedFor
Indicates that a particular region name is used to refer to or designate a specific region or area.
-
C.
regionNamedAfter
Indicates that a geographic region derives its name from a specific person, place, event, or other entity.
-
D.
regionNameCreated
Indicates that a specific region was created with the given name.
-
E.
regionFrom
Indicates that something originates from, is derived from, or is associated with a particular geographic or administrative region.
- F. None of above. chosen
Provenance (7 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_69f348d4891c8190b02bae3c8ecb68b7 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69fe91383a1c81909266e40c3c3ede6c |
completed | May 9, 2026, 1:43 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2b564e373c81908084c5e5514c2f3b |
completed | June 12, 2026, 12:43 a.m. |
| NEDg | Description generation | batch_6a2b570e0ee88190898d1159d69ef4ce |
completed | June 12, 2026, 12:47 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a2b6cb9655c8190955a25f2c262c5e5 |
completed | June 12, 2026, 2:19 a.m. |
| PD | Predicate disambiguation | batch_69fe8fde094081908f0f121664fbb5c7 |
completed | May 9, 2026, 1:37 a.m. |
| PDg | Predicate description generation | batch_69fe9137730c81909d1d57c30566c89a |
completed | May 9, 2026, 1:43 a.m. |
Created at: April 30, 2026, 10:25 p.m.