Triple
T8811331
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DeSean Jackson scored a walk-off punt return touchdown |
E209668
|
entity |
| Predicate | snapSituation |
P84731
|
FINISHED |
| Object | tie game |
—
|
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: tie game | Statement: [DeSean Jackson scored a walk-off punt return touchdown, snapSituation, tie game]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: snapSituation Context triple: [DeSean Jackson scored a walk-off punt return touchdown, snapSituation, tie game]
-
A.
situates
Indicates that one entity places or locates another entity within a particular spatial, contextual, or conceptual setting.
-
B.
refersSituationTo
Indicates that one entity directs or assigns a situation, case, or matter to another entity for attention, handling, or further action.
-
C.
openingSituation
Indicates the initial state, context, or set of conditions that exist at the beginning of an event, interaction, or narrative.
-
D.
scenarioType
Indicates the specific category or kind of situation, context, or use case that an entity or event is associated with.
-
E.
shotOn
Indicates that one entity fired or took a shot at another entity, typically in a sports or combat context.
- 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_69ca8363f3308190a47e3f1ebd51f613 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5fed18f8819087b0282bf8c4208c |
completed | March 31, 2026, 11:59 p.m. |
| PD | Predicate disambiguation | batch_69cc5c1f28ec8190a34311cb412920c2 |
completed | March 31, 2026, 11:43 p.m. |
| PDg | Predicate description generation | batch_69cc5cff3608819081d2d7e5c16d44b7 |
completed | March 31, 2026, 11:47 p.m. |
Created at: March 30, 2026, 6:45 p.m.