Triple
T8811322
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DeSean Jackson scored a walk-off punt return touchdown |
E209668
|
entity |
| Predicate | playResult |
P84728
|
FINISHED |
| Object | touchdown |
—
|
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: touchdown | Statement: [DeSean Jackson scored a walk-off punt return touchdown, playResult, touchdown]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: playResult Context triple: [DeSean Jackson scored a walk-off punt return touchdown, playResult, touchdown]
-
A.
playedUntil
Indicates that an action or event involving playing continued up to a specific time, point, or condition.
-
B.
playerOutcome
Indicates the result or consequence experienced by a player in a game, match, or scenario (such as winning, losing, or drawing).
-
C.
playsProfessional
Indicates that one entity participates in a sport, game, or performance at a professional level for compensation or as a primary occupation in relation to another entity (such as a team, league, or organization).
-
D.
playIn
Indicates that an entity participates or performs in a particular event, context, or location (such as a game, match, or venue).
-
E.
playedCode
Indicates that an entity performed or executed a specific piece of code.
- 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.