Triple
T3045817
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Four Days Marches |
E83443
|
entity |
| Predicate | approximateParticipants |
P1131
|
FINISHED |
| Object | tens of thousands |
—
|
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 | Statement: [Four Days Marches, approximateParticipants, tens of thousands]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approximateParticipants Context triple: [Four Days Marches, approximateParticipants, tens of thousands]
-
A.
numberOfParticipants
chosen
Indicates the total count of entities involved in a particular event, activity, or relationship.
-
B.
approximateAudienceSize
Indicates an estimated number of individuals or entities that are expected to be reached or affected in a given context.
-
C.
guestCountApproximate
Indicates that the number of guests involved is represented as an estimated or approximate count rather than an exact figure.
-
D.
hasApproximateTotalSpeakers
Indicates that an entity is associated with an estimated or roughly calculated number of total speakers, rather than an exact count.
-
E.
employsApproximateNumberOfPeople
Indicates that an entity employs a roughly estimated or approximate number of people, rather than an exact headcount.
- 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_69ad8b24924c8190a9bb6f61d519e4ae |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9bab541c8190a17aca26b3dcfae7 |
completed | March 8, 2026, 3:54 p.m. |
| PD | Predicate disambiguation | batch_69ad961fc62c819087c4c3a44b00847d |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 3:01 p.m.