Triple
T36908563
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stahlhelm, Bund der Frontsoldaten |
E912842
|
entity |
| Predicate | approximatePeakMembership |
P4549
|
FINISHED |
| Object | over 500,000 members |
—
|
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: over 500,000 members | Statement: [Stahlhelm, Bund der Frontsoldaten, approximatePeakMembership, over 500,000 members]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approximatePeakMembership Context triple: [Stahlhelm, Bund der Frontsoldaten, approximatePeakMembership, over 500,000 members]
-
A.
approximateUserPeak
Indicates that one value or event is an estimated or inferred maximum point associated with a particular user.
-
B.
estimatedMemberCount
Indicates the approximate or predicted number of members associated with an entity.
-
C.
memberCountAtPeak
chosen
Indicates the highest number of members that an entity (such as a group or organization) has had at any point in time.
-
D.
approximateOccupation
Indicates that one entity is inferred or estimated to be the occupation or job role of another entity, rather than being known with certainty.
-
E.
peakPopulationApproximate
Indicates that the peak population of an entity is known only approximately rather than as an exact value.
- 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_69f76e879768819085c2fb31a6a5b44b |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69ff97637ad881908c24fe2cc6b036db |
completed | May 9, 2026, 8:21 p.m. |
| PD | Predicate disambiguation | batch_69ff96c43a808190942eeda1934602db |
completed | May 9, 2026, 8:19 p.m. |
Created at: May 3, 2026, 4:13 p.m.