Triple
T10155170
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fran Tarkenton |
E232756
|
entity |
| Predicate | heldRecordUntil |
P37609
|
FINISHED |
| Object | Dan Marino surpassed his records |
—
|
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: Dan Marino surpassed his records | Statement: [Fran Tarkenton, heldRecordUntil, Dan Marino surpassed his records]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heldRecordUntil Context triple: [Fran Tarkenton, heldRecordUntil, Dan Marino surpassed his records]
-
A.
recordHeldUntil
chosen
Indicates that a record remained valid, in force, or applicable up to a specified end time or condition.
-
B.
recordHeldFor
Indicates that one entity is being kept, stored, or maintained on behalf of or in relation to another entity.
-
C.
recordHeld
Indicates that one entity possesses or maintains a particular record associated with another entity or context.
-
D.
heldOn
Indicates that an event or activity takes place at a specific time, date, or occasion.
-
E.
recordHeldIn
Indicates that a record is stored, maintained, or kept within a particular location, system, or repository.
- 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_69ca84885e48819088a31b127cf44904 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cdec38f594819088a7eb73fc25feff |
completed | April 2, 2026, 4:10 a.m. |
| PD | Predicate disambiguation | batch_69cd4ba795808190acc9124c98c6e40f |
completed | April 1, 2026, 4:45 p.m. |
Created at: March 30, 2026, 9:08 p.m.