Triple
T5631685
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Middle Devonian |
E147846
|
entity |
| Predicate | timeScaleRank |
P64687
|
FINISHED |
| Object | middle subdivision of the Devonian |
—
|
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: middle subdivision of the Devonian | Statement: [Middle Devonian, timeScaleRank, middle subdivision of the Devonian]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeScaleRank Context triple: [Middle Devonian, timeScaleRank, middle subdivision of the Devonian]
-
A.
timeScaleType
Indicates the type or category of temporal scaling applied to an event, process, or measurement (e.g., real-time, accelerated, aggregated).
-
B.
timeScaleUnit
Indicates the unit of temporal measurement (such as seconds, minutes, or hours) used to express a given time scale.
-
C.
timescale
Indicates the temporal scale or duration over which a process, relationship, or effect occurs or is evaluated.
-
D.
timeScaleStandard
Indicates the standard or convention used to define, measure, or interpret the time scale associated with an event or process.
-
E.
timeScaleClass
Indicates the classification of a temporal scale or granularity at which an event, process, or relationship is considered or analyzed.
- F. None of above. chosen
Provenance (4 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_69c00907bc8881909ed760d3ed73ef35 |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c0225cdcdc819095034f12c39ef755 |
completed | March 22, 2026, 5:09 p.m. |
| PD | Predicate disambiguation | batch_69c01b1f12ec8190b4b9d9ee31cabe19 |
completed | March 22, 2026, 4:38 p.m. |
| PDg | Predicate description generation | batch_69c01f0684908190ae2d14f0bd2ab892 |
completed | March 22, 2026, 4:55 p.m. |
Created at: March 22, 2026, 3:40 p.m.