Triple
T30376906
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Douma |
E772714
|
entity |
| Predicate | hasReturnees |
P202323
|
FINISHED |
| Object | partial return of residents after 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: partial return of residents after government control | Statement: [Douma, hasReturnees, partial return of residents after government control]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasReturnees Context triple: [Douma, hasReturnees, partial return of residents after government control]
-
A.
returnsTo
Indicates that an entity goes back to a previous location, state, or entity it was associated with before.
-
B.
returnedFor
Indicates that an entity has been sent, given, or brought back in response to, or on behalf of, another entity or prior action.
-
C.
hasReturnVariant
Indicates that an entity has an associated alternative form or version specifically used for returning or sending back.
-
D.
returns
Indicates that one entity gives or sends something back to another entity, often as a result or outcome of a process or action.
-
E.
returnedWith
Indicates that an entity came back or was brought back accompanied by, or in possession of, another specified entity.
- 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_69f2248e3444819081b05712dc6873de |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_6a007241df8081909dbad651fda82aa7 |
completed | May 10, 2026, 11:55 a.m. |
| PD | Predicate disambiguation | batch_6a0071e77ed081908cd618da8977d878 |
completed | May 10, 2026, 11:54 a.m. |
| PDg | Predicate description generation | batch_6a007240adac819087ab65e9733c384f |
completed | May 10, 2026, 11:55 a.m. |
Created at: April 29, 2026, 8 p.m.