Triple
T34516468
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elizabeth Corbet Yeats |
E886163
|
entity |
| Predicate | roleAtCualaPress |
P16130
|
FINISHED |
| Object | manager |
—
|
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: manager | Statement: [Elizabeth Corbet Yeats, roleAtCualaPress, manager]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleAtCualaPress Context triple: [Elizabeth Corbet Yeats, roleAtCualaPress, manager]
-
A.
roleInElEspectador
Indicates that an entity has a specific role or participation in the work titled "El Espectador."
-
B.
roleAtCNN
Indicates that an entity holds or held a specific professional role or position at CNN.
-
C.
editorialRole
Indicates that one entity holds an editorial position or responsibility in relation to another entity, such as a publication, work, or organization.
-
D.
editorialPersonaOf
Indicates that one entity functions as the editorial persona, voice, or identity associated with another entity (such as a publication, platform, or author).
-
E.
publisherRole
chosen
Indicates the specific function, capacity, or responsibility an entity has in relation to publishing a work or resource.
- 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_69f349ccc290819089d8e82698e53cb6 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f7675b12848190a3569cfda29c5b0e |
completed | May 3, 2026, 3:18 p.m. |
| PD | Predicate disambiguation | batch_69f762f4b59481909f70074f11825bfb |
completed | May 3, 2026, 3 p.m. |
Created at: May 1, 2026, 2:01 a.m.