Triple
T21703897
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Abebe Bikila |
E535723
|
entity |
| Predicate | ranWithShoes |
P144982
|
FINISHED |
| Object | 1964 Olympic marathon in Tokyo |
—
|
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: 1964 Olympic marathon in Tokyo | Statement: [Abebe Bikila, ranWithShoes, 1964 Olympic marathon in Tokyo]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ranWithShoes Context triple: [Abebe Bikila, ranWithShoes, 1964 Olympic marathon in Tokyo]
-
A.
ranIn
Indicates that an entity performed a running action within or during a specified location, context, or time frame.
-
B.
requiresShoesOff
Indicates that one entity mandates another to remove their shoes, typically as a condition for entry or participation.
-
C.
traditionalFootwear
Indicates that the relationship involves footwear that is characteristic of, or historically associated with, a particular culture, region, or tradition.
-
D.
ranOn
Indicates that an entity executed or operated on a particular platform, system, or environment.
-
E.
portrayedAsBarefoot
Indicates that an entity is depicted or represented without footwear, showing bare feet.
- 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_69e0c46b44c0819088ab883ebd44e0e8 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef9b82901c81909de242c920fbc164 |
completed | April 27, 2026, 5:23 p.m. |
| PD | Predicate disambiguation | batch_69e6969113cc8190ab69855ef5667e4b |
completed | April 20, 2026, 9:11 p.m. |
| PDg | Predicate description generation | batch_69e69b4aa2b48190830107391e81571a |
completed | April 20, 2026, 9:31 p.m. |
Created at: April 16, 2026, 6:46 p.m.