Triple
T20357965
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Baba Amr district |
E496699
|
entity |
| Predicate | securityStatusPreWar |
P79060
|
FINISHED |
| Object | under Syrian government control |
—
|
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: under Syrian government control | Statement: [Baba Amr district, securityStatusPreWar, under Syrian government control]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: securityStatusPreWar Context triple: [Baba Amr district, securityStatusPreWar, under Syrian government control]
-
A.
statusBeforeWar
Indicates the condition or situation of an entity as it existed prior to the onset of a specified war.
-
B.
legalStatusAfterWar
Indicates the legal condition or classification assigned to an entity as a consequence of, or following the conclusion of, a war or armed conflict.
-
C.
prewarStatus
chosen
Indicates the condition, role, or circumstances of an entity as they existed before a specific war or armed conflict.
-
D.
statusDuringWar
Indicates the role, condition, or classification an entity held specifically during a period of war.
-
E.
statusDuringWorldWarII
Indicates the role, condition, or classification an entity had specifically during the period of World War II.
- 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_69e0b4a3f7f48190b37f354574028ca6 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e67855c3a88190b88839a47d01184d |
completed | April 20, 2026, 7:02 p.m. |
| PD | Predicate disambiguation | batch_69e57636b4808190bc2855af48a3ccdc |
completed | April 20, 2026, 12:41 a.m. |
Created at: April 16, 2026, 11:25 a.m.