Triple
T10818711
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Larry Keller |
E255301
|
entity |
| Predicate | timeOfDeathRelativeToPlay |
P28556
|
FINISHED |
| Object | three years before the main action |
—
|
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: three years before the main action | Statement: [Larry Keller, timeOfDeathRelativeToPlay, three years before the main action]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeOfDeathRelativeToPlay Context triple: [Larry Keller, timeOfDeathRelativeToPlay, three years before the main action]
-
A.
timeOfDeath
chosen
Indicates the specific time at which an entity (typically a person or organism) died.
-
B.
startTimeRelativeToGame
Indicates the time at which an event or action occurs, expressed relative to the start time of the game rather than as an absolute timestamp.
-
C.
timeInTomb
Indicates the duration that an entity remains or has remained inside a tomb.
-
D.
timeBehind
Indicates that one entity occurs or is positioned later in time than another, lagging behind it on a temporal scale.
-
E.
killedAt
Indicates that a killing event occurred at a specific location or time associated with the entities involved.
- 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_69d6aa8081448190a9324184f2bd1c26 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7344866f88190be4addb7c8020fce |
completed | April 9, 2026, 5:08 a.m. |
| PD | Predicate disambiguation | batch_69d70d1bf3648190b36fa96ea018e0dc |
completed | April 9, 2026, 2:21 a.m. |
Created at: April 8, 2026, 9:18 p.m.