Triple
T30302184
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1977 NFL Draft |
E770680
|
entity |
| Predicate | roundsReducedFrom |
P102026
|
FINISHED |
| Object | 17 |
—
|
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: 17 | Statement: [1977 NFL Draft, roundsReducedFrom, 17]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roundsReducedFrom Context triple: [1977 NFL Draft, roundsReducedFrom, 17]
-
A.
roundsReducedSecurity
Indicates that the number of rounds in a process or protocol has been decreased in a way that lowers its security level.
-
B.
reducedNumberOf
chosen
Indicates that the subject has a smaller quantity or count of the specified object or attribute compared to a prior state or reference level.
-
C.
reachedRound
Indicates that an entity has advanced to or attained a particular round or stage within a process, event, or competition.
-
D.
hasProperRounds
Indicates that an entity is associated with rounds that meet specified standards or criteria for being considered proper or valid.
-
E.
roundCount
Indicates the number of discrete rounds or iterations that have occurred or are allocated within a process, event, or interaction.
- 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_69f224881b948190b8c4921b250a44a3 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6813b03c881909786514932f103f3 |
completed | May 2, 2026, 10:56 p.m. |
| PD | Predicate disambiguation | batch_69f6760216108190bbb708d53a6c2c25 |
completed | May 2, 2026, 10:09 p.m. |
Created at: April 29, 2026, 7:49 p.m.