Triple
T31346362
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amhara regional forces |
E799456
|
entity |
| Predicate | regionOfClaim |
P647
|
FINISHED |
| Object | Western Tigray Zone |
—
|
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: Western Tigray Zone | Statement: [Amhara regional forces, regionOfClaim, Western Tigray Zone]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regionOfClaim Context triple: [Amhara regional forces, regionOfClaim, Western Tigray Zone]
-
A.
regionOfLoss
Indicates the anatomical or spatial area where a loss, damage, or deficit occurs or is localized.
-
B.
countryOfClaim
Indicates the country in which a claim (such as legal, insurance, or patent claim) is formally filed or asserted.
-
C.
claimsTerritory
chosen
Indicates that one entity asserts ownership, control, or sovereign rights over a specific geographic area or region.
-
D.
claimsJurisdictionOver
Indicates that one authority or governing body asserts legal power or control over a particular area, matter, or entity.
-
E.
regionImplied
Indicates that a broader or more general region is inferred or assumed from a given, more specific regional reference.
- 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_69f224e51614819083141459a080e97c |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fe779248c081909f0ed1a2a0df23db |
completed | May 8, 2026, 11:53 p.m. |
| PD | Predicate disambiguation | batch_69fe76eaf6d48190998bc7168749cc42 |
completed | May 8, 2026, 11:51 p.m. |
Created at: April 29, 2026, 9:17 p.m.