Triple
T29398498
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Erebuni District of Yerevan |
E745568
|
entity |
| Predicate | hasFoundingSiteOf |
P4560
|
FINISHED |
| Object | Yerevan |
—
|
NE NERFINISHED |
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: Yerevan | Statement: [Erebuni District of Yerevan, hasFoundingSiteOf, Yerevan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFoundingSiteOf Context triple: [Erebuni District of Yerevan, hasFoundingSiteOf, Yerevan]
-
A.
foundedCityOnSiteOf
Indicates that a city was established on the same physical location where another settlement or city previously existed.
-
B.
foundedOnSiteOf
Indicates that something was established or built at the same physical location where another, earlier entity or structure previously existed.
-
C.
foundedAsResidenceOf
Indicates that something was originally established or created to serve as the residence of a particular person or group.
-
D.
placeFounded
chosen
Indicates the location where an entity (such as an organization or institution) was originally established or founded.
-
E.
foundedAsSettlementFor
Indicates that one entity was originally established specifically to serve as a settlement for another entity (such as a group, population, or community).
- 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_69f0a79dfabc81908755382ee47791e2 |
completed | April 28, 2026, 12:27 p.m. |
| NER | Named-entity recognition | batch_69f7c777e924819081a6634f549fe552 |
completed | May 3, 2026, 10:08 p.m. |
| PD | Predicate disambiguation | batch_69f7c475c58c8190a883554231e88c88 |
completed | May 3, 2026, 9:56 p.m. |
Created at: April 28, 2026, 2:48 p.m.