Triple
T36817634
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eastern Tigray Zone |
E909787
|
entity |
| Predicate | borderTypeToEritrea |
P201384
|
FINISHED |
| Object | international border |
—
|
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: international border | Statement: [Eastern Tigray Zone, borderTypeToEritrea, international border]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: borderTypeToEritrea Context triple: [Eastern Tigray Zone, borderTypeToEritrea, international border]
-
A.
borderTypeWithEthiopia
Indicates the specific nature or classification of the border relationship that an entity has with Ethiopia.
-
B.
borderTypeWithYemen
Indicates the type or nature of the border that exists between a given entity and Yemen.
-
C.
borderTypeWithSouthSudan
Indicates the type or nature of the border that an entity shares with South Sudan.
-
D.
borderTypeWithGulfOfAden
Indicates that an entity’s border is specifically characterized as adjoining or interacting with the Gulf of Aden.
-
E.
borderTypeWithArmenia
Indicates the type or nature of the border relationship that an entity has with Armenia.
- F. None of above. chosen
Provenance (4 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_69f76e7dd13c81908c60b05adb49eeb5 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69ffef812da48190b875a7376b24f92d |
completed | May 10, 2026, 2:37 a.m. |
| PD | Predicate disambiguation | batch_69ffedecd580819097851b1473fdd6ed |
completed | May 10, 2026, 2:31 a.m. |
| PDg | Predicate description generation | batch_69ffef8003c081909ec2413b4ea08d43 |
completed | May 10, 2026, 2:37 a.m. |
Created at: May 3, 2026, 4:13 p.m.