Triple
T36885284
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fortescue Group |
E911591
|
entity |
| Predicate | ageApproximateMa |
P82273
|
FINISHED |
| Object | 2800–2700 Ma |
—
|
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: 2800–2700 Ma | Statement: [Fortescue Group, ageApproximateMa, 2800–2700 Ma]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ageApproximateMa Context triple: [Fortescue Group, ageApproximateMa, 2800–2700 Ma]
-
A.
approximateAgeMa
chosen
Indicates that one entity has an estimated or approximate age value relative to another reference (such as a person or event).
-
B.
latestAgeApproxMa
Indicates the most recent estimated age of something expressed in millions of years (Ma), typically as an approximate upper or younger bound in time.
-
C.
age_Ma
Indicates the age of something measured in millions of years (mega-annum).
-
D.
earliestAgeApproxMa
Indicates the approximate minimum age in millions of years at which something first occurred, formed, or existed.
-
E.
endAgeMa
Indicates the age (in years) at which a marriage or marital relationship ends.
- 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_69f76e8335908190b77e7e11d0e80820 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f9fd6d4ec48190942f3abf44bd056c |
completed | May 5, 2026, 2:23 p.m. |
| PD | Predicate disambiguation | batch_69f7cf7890008190a8bc355ff2d61c86 |
completed | May 3, 2026, 10:43 p.m. |
Created at: May 3, 2026, 4:13 p.m.