Triple
T38430722
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arnold von Winkelried |
E903790
|
entity |
| Predicate | earliestDetailedAccountBy |
P150436
|
FINISHED |
| Object | Aegidius Tschudi |
—
|
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: Aegidius Tschudi | Statement: [Arnold von Winkelried, earliestDetailedAccountBy, Aegidius Tschudi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: earliestDetailedAccountBy Context triple: [Arnold von Winkelried, earliestDetailedAccountBy, Aegidius Tschudi]
-
A.
earliestSurvivingNativeAccountOf
chosen
Indicates that one entity is the oldest known surviving account or record created by a native or indigenous source describing another entity.
-
B.
contemporaryAccountBy
Indicates that the account or description of an event or subject was created by someone who lived at the same time as, and was a contemporary of, that event or subject.
-
C.
hasHistoricalDetail
Indicates that something includes or is associated with specific information about past events, contexts, or developments.
-
D.
earliestDate
Indicates the earliest point in time at which an associated event, state, or relationship is considered to begin or be valid.
-
E.
historicalBalance
Indicates a relationship where an entity’s past or previous balance amount is recorded or referenced over time.
- 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_69f76e6a2024819081aa04f4932f89d2 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fd2cf39b0c8190811b8a6fa9410560 |
completed | May 8, 2026, 12:23 a.m. |
| PD | Predicate disambiguation | batch_69fd2ad8dd988190a9899701ba00d917 |
completed | May 8, 2026, 12:14 a.m. |
Created at: May 3, 2026, 4:31 p.m.