Triple
T2000112
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Munich air disaster |
E43448
|
entity |
| Predicate | matchContext |
P35407
|
FINISHED |
| Object | return from European Cup tie against Red Star Belgrade |
—
|
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: return from European Cup tie against Red Star Belgrade | Statement: [Munich air disaster, matchContext, return from European Cup tie against Red Star Belgrade]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: matchContext Context triple: [Munich air disaster, matchContext, return from European Cup tie against Red Star Belgrade]
-
A.
matchStructure
Indicates that two entities share the same structural pattern or organization, regardless of their specific content or values.
-
B.
matchType
Indicates the specific category or nature of how two or more entities correspond or align with each other within a given context.
-
C.
matches
Indicates that two entities correspond to or are in agreement with each other according to some defined criteria or pattern.
-
D.
typicalMatchType
Indicates the usual or most common type of match or pairing that characterizes how two entities are related or aligned.
-
E.
usesMatchesFrom
Indicates that one entity relies on or incorporates matches (e.g., pattern matches, rule matches, or result matches) produced by another entity or process.
- F. None of above. chosen
Provenance (4 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_69a88715dbbc8190b2299e29e955d997 |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb91055d88190a980e7b42e5895d4 |
completed | March 7, 2026, 5:35 a.m. |
| PD | Predicate disambiguation | batch_69abb79c97d48190b3147430ed39faa9 |
completed | March 7, 2026, 5:29 a.m. |
| PDg | Predicate description generation | batch_69abb90ec7948190bbfb0329e9e67cca |
completed | March 7, 2026, 5:35 a.m. |
Created at: March 4, 2026, 7:37 p.m.