Triple
T31082640
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Fada |
E792141
|
entity |
| Predicate | casualtiesLibyanCaptured |
P172856
|
FINISHED |
| Object | approximately 1000 |
—
|
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: approximately 1000 | Statement: [Battle of Fada, casualtiesLibyanCaptured, approximately 1000]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: casualtiesLibyanCaptured Context triple: [Battle of Fada, casualtiesLibyanCaptured, approximately 1000]
-
A.
casualtiesLibya
Indicates the occurrence or count of people killed or injured in events taking place in Libya.
-
B.
casualtiesAtTobruk
Indicates that an entity experienced casualties (killed, wounded, or missing) in connection with the events at Tobruk.
-
C.
casualtiesEgyptianSide
Indicates the number of people killed or injured who belong to, or are counted as part of, the Egyptian side in a conflict or incident.
-
D.
statusInLibya
Indicates the legal, social, or political condition or standing that an entity holds within the context of Libya.
-
E.
casualtiesMahdistSide
Indicates the number of people killed, wounded, or otherwise harmed on the Mahdist side in a conflict or violent event.
- 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_69f224ce48348190bd0fc23f656ed683 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6b0d21dd08190a9883ff71c94c71c |
completed | May 3, 2026, 2:20 a.m. |
| PD | Predicate disambiguation | batch_69f6aca3dedc81908b519d53d2909868 |
completed | May 3, 2026, 2:02 a.m. |
| PDg | Predicate description generation | batch_69f6afeaaef88190aefa97e83f8db906 |
completed | May 3, 2026, 2:16 a.m. |
Created at: April 29, 2026, 9:02 p.m.