Triple
T20182768
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roshambo |
E492772
|
entity |
| Predicate | hasDrawCondition |
P1255
|
FINISHED |
| Object | both players choose same gesture |
—
|
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: both players choose same gesture | Statement: [Roshambo, hasDrawCondition, both players choose same gesture]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDrawCondition Context triple: [Roshambo, hasDrawCondition, both players choose same gesture]
-
A.
hasDrawType
Indicates that an entity is associated with a specific manner, style, or category of drawing or graphical rendering.
-
B.
hasCondition
chosen
Indicates that an entity possesses, experiences, or is affected by a particular condition or state.
-
C.
hasOpeningCondition
Indicates that a relationship or action is subject to a specific initial condition that must be met before it can begin or take effect.
-
D.
hasNumberOfConditions
Indicates that an entity is associated with a specific count of conditions it has or is subject to.
-
E.
hasMainDraw
Indicates that an entity includes or is associated with a primary or central component, event, or section referred to as the "main draw."
- 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_69da6268a034819081cbd9ea5a1c9475 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e668ef9370819091a8479f811002a9 |
completed | April 20, 2026, 5:57 p.m. |
| PD | Predicate disambiguation | batch_69e55b11124c8190babacf2a0fe2d057 |
completed | April 19, 2026, 10:45 p.m. |
Created at: April 11, 2026, 11:36 p.m.