Triple
T34871451
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peter Shilton |
E1005761
|
entity |
| Predicate | facedGoal |
P104229
|
FINISHED |
| Object | Diego Maradona "Hand of God" goal |
—
|
NE NERFINISHED |
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: Diego Maradona "Hand of God" goal | Statement: [Peter Shilton, facedGoal, Diego Maradona "Hand of God" goal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: facedGoal Context triple: [Peter Shilton, facedGoal, Diego Maradona "Hand of God" goal]
-
A.
goalkeeperFaced
chosen
Indicates that a goalkeeper encountered and had to respond to a particular shot, attempt, or offensive action during play.
-
B.
goalIn
Indicates that one entity’s objective, aim, or intended outcome is located within, directed toward, or achieved inside another entity or context.
-
C.
laterGoal
Indicates that one goal occurs or is intended to be achieved after another goal in time.
-
D.
goalsFor
Indicates the number of goals scored by one participant or team in favor of a particular side or match context.
-
E.
formerGoal
Indicates that an entity previously had a particular goal or objective, but no longer has it.
- 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_69f76dbde1c08190a24e7f9beb564c8d |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f782f4f10081908f97f6d0d2dbeec7 |
completed | May 3, 2026, 5:16 p.m. |
| PD | Predicate disambiguation | batch_69f780ff71cc8190a67e71076fbad81a |
completed | May 3, 2026, 5:08 p.m. |
Created at: May 3, 2026, 4 p.m.