Triple
T23220531
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Edyth Susie Herbst |
E580877
|
entity |
| Predicate | hasFamilyName |
P18
|
FINISHED |
| Object | Herbst |
—
|
NE NERFINISHED |
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: Herbst | Statement: [Edyth Susie Herbst, hasFamilyName, Herbst]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Herbst Context triple: [Edyth Susie Herbst, hasFamilyName, Herbst]
-
A.
Herbst
chosen
Herbst is a German-language surname borne by various individuals, including those of German or Central European origin.
-
B.
Automne
Automne is a river in northern France that serves as a tributary of the Oise.
-
C.
Autumn (Herbst)
"Autumn (Herbst)" is an expressionist painting by Russian-Swiss artist Marianne von Werefkin, reflecting her vivid color palette and emotionally charged, modernist style.
-
D.
Autumn
"Autumn" is a brief, imagist-style poem by T. E. Hulme that vividly captures the mood and atmosphere of the fall season through precise, concrete imagery.
-
E.
Autumn
Autumn is a feminine given name often associated with the fall season and used in various English-speaking countries.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e2460389408190be74f41d217799a9 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f1916870148190853874e6cf26bbc7 |
completed | April 29, 2026, 5:04 a.m. |
Created at: April 17, 2026, 4:08 p.m.