Triple
T3367509
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Khan Yunis refugee camp |
E70871
|
entity |
| Predicate | hasRefugeeStatus |
P9069
|
FINISHED |
| Object | Palestine refugees registered with UNRWA |
—
|
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: Palestine refugees registered with UNRWA | Statement: [Khan Yunis refugee camp, hasRefugeeStatus, Palestine refugees registered with UNRWA]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRefugeeStatus Context triple: [Khan Yunis refugee camp, hasRefugeeStatus, Palestine refugees registered with UNRWA]
-
A.
hasRefugeePopulation
chosen
Indicates that an entity hosts, contains, or is associated with a population of refugees.
-
B.
receivedAsylumFrom
Indicates that one entity was granted asylum or refuge by another entity, typically a state or institution.
-
C.
attemptedToSeekAsylumIn
Indicates that an entity tried, but may not have succeeded, to obtain asylum in a particular place or country.
-
D.
hasRefugeeCamp
Indicates that a location or entity hosts, contains, or is the site of a refugee camp.
-
E.
soughtAsylumAt
Indicates that an individual or group applied for protection or refuge at a particular country, institution, or authority.
- 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_69ad85a729d48190afd789cd8417f289 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb2890480819082fe2e3c2874cece |
completed | March 8, 2026, 5:31 p.m. |
| PD | Predicate disambiguation | batch_69ada4317e288190ab7d0f66e9dba65f |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:13 p.m.