Triple
T23237578
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nadia Conners |
E581344
|
entity |
| Predicate | hasWorkedOnTopic |
P81453
|
FINISHED |
| Object | climate change |
—
|
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: climate change | Statement: [Nadia Conners, hasWorkedOnTopic, climate change]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWorkedOnTopic Context triple: [Nadia Conners, hasWorkedOnTopic, climate change]
-
A.
hasWorksAbout
chosen
Indicates that one entity (such as a creator, collection, or source) includes or is associated with works whose subject or focus is another entity.
-
B.
hasWorkedOnPolicy
Indicates that an entity has participated in the development, modification, or implementation of a specific policy.
-
C.
hasWorkedIn
Indicates that a person has been employed or has performed work within a particular organization, location, or domain for some period of time.
-
D.
hasWorkDedicatedTo
Indicates that one entity has a work (such as a book, artwork, or composition) that is formally dedicated to another entity.
-
E.
hasCatalogedWorkOn
Indicates that an entity has formally recorded, listed, or documented another entity as a work within a catalog or collection.
- 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_69e2460556f88190be1744a84a84173f |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f192ea590c81908cd677d89f67d49f |
completed | April 29, 2026, 5:11 a.m. |
| PD | Predicate disambiguation | batch_69effcdadec0819092ec1749ee453b4e |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 4:09 p.m.