Triple
T30880490
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roger Mason |
E786595
|
entity |
| Predicate | notableDiscoveryType |
P170755
|
FINISHED |
| Object | fossils |
—
|
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: fossils | Statement: [Roger Mason, notableDiscoveryType, fossils]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableDiscoveryType Context triple: [Roger Mason, notableDiscoveryType, fossils]
-
A.
historicalDiscovery
Indicates that one entity is the discoverer or originator of another entity in a historical context, capturing the act of first finding, identifying, or documenting it.
-
B.
madeDiscoveryOn
Indicates that an entity discovered or identified something on a specific date or at a specific point in time.
-
C.
notableDiscoveryAtSite
Indicates that an entity is recognized for having made an important discovery at a particular site.
-
D.
inspiredDiscoveryOf
Indicates that one entity’s ideas, actions, or work motivated or led directly to another entity’s discovery.
-
E.
scientificAchievement
chosen
Indicates that an entity has accomplished a notable result, discovery, or advancement in a scientific field.
- 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_69f224bae17c8190bb3a6a28e3d019df |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_6a037c876524819098545e6037d3107d |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379e2fac0819089b522db3260028c |
completed | May 12, 2026, 7:05 p.m. |
Created at: April 29, 2026, 8:48 p.m.