Triple
T32023950
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pound–Rebka experiment |
E817767
|
entity |
| Predicate | sourcePosition |
P66908
|
FINISHED |
| Object | bottom of tower |
—
|
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: bottom of tower | Statement: [Pound–Rebka experiment, sourcePosition, bottom of tower]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sourcePosition Context triple: [Pound–Rebka experiment, sourcePosition, bottom of tower]
-
A.
hasSourcePosition
chosen
Indicates that something originates from, is located at, or is associated with a specific source position or starting point.
-
B.
labelCodePosition
Indicates assigning a specific label to a particular position or location within a code sequence or code structure.
-
C.
sourceLocatedOn
Indicates that the source entity is physically situated on the surface or area of the target entity.
-
D.
positionInProgram
Indicates the specific place or order that something occupies within a larger program or sequence of program elements.
-
E.
source
Indicates that something originates from, is derived from, or is provided by a particular entity or location.
- 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_69f348fb04e4819081f4eab040ed7959 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f72921cf2c8190909bb53f78bcc890 |
completed | May 3, 2026, 10:53 a.m. |
| PD | Predicate disambiguation | batch_69f7283d8cec8190b524c144948bc4ec |
completed | May 3, 2026, 10:49 a.m. |
Created at: May 1, 2026, 12:17 a.m.