Triple
T2663315
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dukla Pass |
E54773
|
entity |
| Predicate | battleCasualtiesEstimate |
P6773
|
FINISHED |
| Object | tens of thousands of soldiers |
—
|
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: tens of thousands of soldiers | Statement: [Dukla Pass, battleCasualtiesEstimate, tens of thousands of soldiers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: battleCasualtiesEstimate Context triple: [Dukla Pass, battleCasualtiesEstimate, tens of thousands of soldiers]
-
A.
militaryCasualtiesEstimate
chosen
Indicates an estimated number of people killed, wounded, or missing as a result of military conflict or operations.
-
B.
casualtiesEstimate
Indicates an estimated number of people killed, injured, or otherwise harmed as a result of an event or incident.
-
C.
deathTollEstimate
Indicates an estimated number of deaths attributed to a particular event, cause, or period.
-
D.
plannedCasualtyExpectations
Indicates that an entity has estimated or anticipated the number or extent of casualties expected to result from a planned action or event.
-
E.
UScasualties
Indicates the number or occurrence of casualties suffered by the United States in a given conflict, event, or situation.
- 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_69ab49e028948190b97e01d73548b1d9 |
completed | March 6, 2026, 9:40 p.m. |
| NER | Named-entity recognition | batch_69abd96b9f1c8190a8a9460ca88a9aaf |
completed | March 7, 2026, 7:53 a.m. |
| PD | Predicate disambiguation | batch_69abd81768748190bd965f367cf6ef37 |
completed | March 7, 2026, 7:47 a.m. |
Created at: March 6, 2026, 9:53 p.m.