Triple
T36127352
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frau Diller’s shop |
E1044918
|
entity |
| Predicate | requiresGreeting |
P4600
|
FINISHED |
| Object | Heil Hitler |
—
|
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: Heil Hitler | Statement: [Frau Diller’s shop, requiresGreeting, Heil Hitler]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: requiresGreeting Context triple: [Frau Diller’s shop, requiresGreeting, Heil Hitler]
-
A.
requiresStandingEtiquette
Indicates that the situation or action necessitates following proper etiquette or manners specifically while standing.
-
B.
typicalGreeting
chosen
Indicates the standard or commonly used way one entity greets another in a given context.
-
C.
requiresStandingWhenAddressing
Indicates that one entity must be standing when formally addressing or speaking to another entity.
-
D.
confirmationRequirement
Indicates that an action, decision, or change is contingent on receiving explicit confirmation from a specified party or process.
-
E.
hasEtiquette
Indicates that an entity follows or embodies proper manners, social norms, or courteous behavior in interactions with others.
- 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_69f76e356c908190abc6ca1e6a05b011 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ffcb5536d88190bfc2e00b854cacfb |
completed | May 10, 2026, 12:03 a.m. |
| PD | Predicate disambiguation | batch_69ffc900c2a081909dea04aa60566923 |
completed | May 9, 2026, 11:53 p.m. |
Created at: May 3, 2026, 4:08 p.m.