Triple
T24244678
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lishan Didan |
E603330
|
entity |
| Predicate | primaryCountryOfOrigin |
P26
|
FINISHED |
| Object | Iran |
—
|
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: Iran | Statement: [Lishan Didan, primaryCountryOfOrigin, Iran]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryCountryOfOrigin Context triple: [Lishan Didan, primaryCountryOfOrigin, Iran]
-
A.
parentCountryOfOrigin
Indicates that one country is the original source or homeland from which another country historically emerged or originated.
-
B.
primaryUseCountry
Indicates the country in which something is primarily used or most commonly utilized.
-
C.
countryOfOrigin
chosen
Indicates the country from which an entity originally comes or was first produced, created, or established.
-
D.
primaryLocationCountry
Indicates the country that serves as the main or primary location associated with the subject.
-
E.
primaryAncestralCountry
Indicates the country that is considered the main place of origin for an individual’s or group’s ancestors.
- 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_69e2953f631c819097cbb421046bd417 |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f28b82e13c819083ca524e47ed66b1 |
completed | April 29, 2026, 10:51 p.m. |
| PD | Predicate disambiguation | batch_69f1c448abec8190b87cbf9ed419a309 |
completed | April 29, 2026, 8:41 a.m. |
Created at: April 18, 2026, 12:04 a.m.