Triple
T36259652
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anschluss-era Austria |
E892045
|
entity |
| Predicate | hasLocalLeader |
P103923
|
FINISHED |
| Object | Arthur Seyss-Inquart |
—
|
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: Arthur Seyss-Inquart | Statement: [Anschluss-era Austria, hasLocalLeader, Arthur Seyss-Inquart]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLocalLeader Context triple: [Anschluss-era Austria, hasLocalLeader, Arthur Seyss-Inquart]
-
A.
hasLeader
Indicates that one entity serves as the leader or head of another entity.
-
B.
hasLeaderAtLocation
chosen
Indicates that a specified leader is associated with or holds leadership responsibilities at a particular location.
-
C.
hasLeaderParticipant
Indicates that an entity participates in an event or activity in the role of a leader.
-
D.
hasMajorityLeader
Indicates that one entity serves as the primary or leading decision-making authority (majority leader) for another entity, typically within a governing or organizational body.
-
E.
hasProminentLeaderFromState
Indicates that an entity has a leading or highly influential figure whose origin or primary affiliation is with a specified state.
- 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_69f76e4699188190af045b11a840ce31 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ff519b65f081909902ba83b775ef85 |
completed | May 9, 2026, 3:24 p.m. |
| PD | Predicate disambiguation | batch_69ff506fccdc8190bd93269589040aed |
completed | May 9, 2026, 3:19 p.m. |
Created at: May 3, 2026, 4:09 p.m.