Triple
T27337938
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sidi Ferruch |
E690007
|
entity |
| Predicate | invasionOf |
P21625
|
FINISHED |
| Object | Regency of Algiers |
—
|
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: Regency of Algiers | Statement: [Sidi Ferruch, invasionOf, Regency of Algiers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: invasionOf Context triple: [Sidi Ferruch, invasionOf, Regency of Algiers]
-
A.
wasInvadedBy
chosen
Indicates that a place or territory was subjected to an incursion or attack carried out by another entity or group.
-
B.
invade
Indicates entering another entity’s territory or domain, typically by force or without permission, in order to take control or exert dominance.
-
C.
invasionAddressed
Indicates that an invasion event has been responded to or dealt with through some form of action, intervention, or resolution.
-
D.
invasionCodename
Indicates the codename assigned to a specific military invasion operation.
-
E.
plannedInvasionOf
Indicates that one entity has formulated or organized an invasion targeting another entity.
- 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_69ef355e5b388190a8fc1eba9b4a6656 |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69f62ad0b7b88190a69f8e8b2fc9fe3e |
completed | May 2, 2026, 4:48 p.m. |
| PD | Predicate disambiguation | batch_69f623a91b9c8190b2e2fdbc55cb89b6 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 11:41 a.m.