Triple
T31438190
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tigray Defense Forces |
E801991
|
entity |
| Predicate | launchedOffensiveIn |
P16144
|
FINISHED |
| Object | Afar Region |
—
|
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: Afar Region | Statement: [Tigray Defense Forces, launchedOffensiveIn, Afar Region]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: launchedOffensiveIn Context triple: [Tigray Defense Forces, launchedOffensiveIn, Afar Region]
-
A.
offensiveOperationBy
Indicates that an offensive military or strategic operation is carried out by a specified actor or entity.
-
B.
offensiveOperation
chosen
Indicates an action or campaign in which a party actively initiates hostile or military measures against an opponent.
-
C.
plannedAttackWith
Indicates that one entity has prepared or organized an attack using or involving another entity as the means or instrument of that attack.
-
D.
offensiveForce
Indicates the use or application of aggressive or attacking power or violence by one entity against another.
-
E.
offensiveStrategy
Indicates a strategic approach focused on attacking or aggressively advancing against an opponent.
- 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_69f348c475348190bf579ca858eec77c |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6d16f5cb881908eed141afaaa0b51 |
completed | May 3, 2026, 4:39 a.m. |
| PD | Predicate disambiguation | batch_69f6cfe45554819089cbbd538d992132 |
completed | May 3, 2026, 4:32 a.m. |
Created at: April 30, 2026, 9:03 p.m.