Triple
T19317122
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Millennium Ecosystem Assessment |
E483127
|
entity |
| Predicate | numberOfExpertsInvolved |
P86609
|
FINISHED |
| Object | over 1300 |
—
|
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: over 1300 | Statement: [Millennium Ecosystem Assessment, numberOfExpertsInvolved, over 1300]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfExpertsInvolved Context triple: [Millennium Ecosystem Assessment, numberOfExpertsInvolved, over 1300]
-
A.
hasNumberOfIndependentExperts
chosen
Indicates the quantity of independent experts associated with or involved in a given entity or context.
-
B.
estimatedInformants
Indicates that one entity has made an approximate or inferred determination of the number or identity of informants associated with another entity or situation.
-
C.
numberOfScientists
Indicates the quantity of scientists associated with a given entity or context.
-
D.
numberOfCoFounders
Indicates the count of individuals who jointly founded a given entity.
-
E.
numberOfExecutives
Indicates the total count of executives associated with a given entity or context.
- 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_69d8e8d04d5c8190baa816986f2b1d1e |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e60d843640819089ff3738aae29eb1 |
completed | April 20, 2026, 11:27 a.m. |
| PD | Predicate disambiguation | batch_69e4dd0ef66881909d489d634eee817a |
completed | April 19, 2026, 1:47 p.m. |
Created at: April 10, 2026, 1:32 p.m.