Triple
T23837411
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rindler horizon |
E590890
|
entity |
| Predicate | hasLimitingSpeed |
P2129
|
FINISHED |
| Object | speed of light for signals approaching the horizon |
—
|
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: speed of light for signals approaching the horizon | Statement: [Rindler horizon, hasLimitingSpeed, speed of light for signals approaching the horizon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLimitingSpeed Context triple: [Rindler horizon, hasLimitingSpeed, speed of light for signals approaching the horizon]
-
A.
hasSpeedLimit
chosen
Indicates that a specified maximum allowable speed is imposed on the associated entity or context.
-
B.
hasSpeedLimitCharacteristic
Indicates that an entity is associated with a specific speed limit property or constraint.
-
C.
hasSpeedRestriction
Indicates that an entity is subject to a specified limit on its allowable speed.
-
D.
hasVariableSpeedLimits
Indicates that the subject is associated with speed limits that can change depending on conditions, time, or location.
-
E.
hasSpeedLimitPolicy
Indicates that an entity is associated with a specific policy defining rules or constraints on allowable speed limits.
- 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_69e25d1de32c8190a907afe9c3d6cd6d |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1c883c7108190b3cce6fec0b8609a |
completed | April 29, 2026, 8:59 a.m. |
| PD | Predicate disambiguation | batch_69f156036ad48190bc2ffdaf39218bcb |
completed | April 29, 2026, 12:51 a.m. |
Created at: April 17, 2026, 8:07 p.m.