Triple
T36093527
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cambridge Backs |
E1043993
|
entity |
| Predicate | runsBehind |
P65959
|
FINISHED |
| Object | University of Cambridge colleges |
—
|
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: University of Cambridge colleges | Statement: [Cambridge Backs, runsBehind, University of Cambridge colleges]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: runsBehind Context triple: [Cambridge Backs, runsBehind, University of Cambridge colleges]
-
A.
runsBeneath
Indicates that one entity extends or moves below another entity along its length or span.
-
B.
runningBack
Indicates that one entity is acting as a running back in relation to another entity, typically within the context of an American football play or team.
-
C.
isBehind
chosen
Indicates that one entity is positioned to the rear of another entity along a relevant spatial or directional axis.
-
D.
runs
Indicates that an entity moves swiftly on foot, typically using its legs in a continuous, rapid motion.
-
E.
RunsBattedIn
Indicates the number of runs a batter causes to score as a direct result of their plate appearance or action.
- 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_69f76e32d60c8190ba781ffaaab4aa3d |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7b3e2f3c08190be4fd1ae4fa1266d |
completed | May 3, 2026, 8:45 p.m. |
| PD | Predicate disambiguation | batch_69f7b1bcc47081909fe7d592ac69006c |
completed | May 3, 2026, 8:36 p.m. |
Created at: May 3, 2026, 4:08 p.m.