Triple
T18905030
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hochfirstschanze |
E462437
|
entity |
| Predicate | hasRunIn |
P122966
|
FINISHED |
| Object | inrun tower |
—
|
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: inrun tower | Statement: [Hochfirstschanze, hasRunIn, inrun tower]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRunIn Context triple: [Hochfirstschanze, hasRunIn, inrun tower]
-
A.
hasRun
Indicates that an entity has performed or completed a running activity or event at least once in the past.
-
B.
hasRunType
Indicates the type or category of a run associated with an entity (e.g., execution mode, run classification, or run configuration).
-
C.
hasInrunLength
chosen
Indicates the length of the inrun portion (approach or run-up) associated with an activity, structure, or course.
-
D.
hasCalledProgram
Indicates that one program has invoked or executed another program.
-
E.
hasLaunchedFor
Indicates that an entity (such as a product, feature, or service) has been officially released or made available specifically for another entity (such as a user, group, market, or platform).
- 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_69d8dcfd05bc819088903cca13cc2846 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c52c121c8190a2057b99c723694b |
completed | April 20, 2026, 6:18 a.m. |
| PD | Predicate disambiguation | batch_69e4a2e27e1481908a8da10b28f07875 |
completed | April 19, 2026, 9:39 a.m. |
Created at: April 10, 2026, 11:58 a.m.