Triple
T8912177
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Somme 1916 |
E212209
|
entity |
| Predicate | firstDayDeaths |
P1785
|
FINISHED |
| Object | approximately 19,000 British soldiers killed |
—
|
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 19,000 British soldiers killed | Statement: [Somme 1916, firstDayDeaths, approximately 19,000 British soldiers killed]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstDayDeaths Context triple: [Somme 1916, firstDayDeaths, approximately 19,000 British soldiers killed]
-
A.
firstDayKilledApproximate
Indicates that the approximate date on which the subject was killed corresponds to the first day of a specified time period or event.
-
B.
deathToll
chosen
Indicates the number of deaths resulting from a particular event, situation, or cause.
-
C.
deathApprox
Indicates that an entity’s death occurred at an approximate, rather than exact, time or date.
-
D.
deathTollEstimate
Indicates an estimated number of deaths attributed to a particular event, cause, or period.
-
E.
causeOfDeath
Indicates the specific factor, event, or condition that directly resulted in an entity’s death.
- 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_69ca8393b1808190bd4336787ffa2c40 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6525d1408190a76522d7c4ac37da |
completed | April 1, 2026, 12:21 a.m. |
| PD | Predicate disambiguation | batch_69cc5ecf55248190a29f00fbf99f13c4 |
completed | March 31, 2026, 11:54 p.m. |
Created at: March 30, 2026, 6:56 p.m.