Triple
T26098008
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Akamai Technologies |
E658324
|
entity |
| Predicate | roleOfTomLeighton |
P162913
|
FINISHED |
| Object | Chief Executive Officer |
—
|
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: Chief Executive Officer | Statement: [Akamai Technologies, roleOfTomLeighton, Chief Executive Officer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleOfTomLeighton Context triple: [Akamai Technologies, roleOfTomLeighton, Chief Executive Officer]
-
A.
roleOfTomWopat
Indicates that the specified role or character is portrayed or performed by Tom Wopat.
-
B.
roleOfTomTucker
Indicates that the specified role or position is held or performed by Tom Tucker.
-
C.
Jack Hively
Indicates a relationship or action involving the person named Jack Hively, such as authorship, direction, or participation in a work or event.
-
D.
roleOfVictorFeldbrill
Indicates the professional role, position, or capacity held by Victor Feldbrill in a given context.
-
E.
roleOfHarryVanda
Indicates that the specified role or function is held or performed by Harry Vanda in relation to another entity or context.
- F. None of above. chosen
Provenance (4 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_69ee5bc09c288190bc42a11972841383 |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69f62e83045c8190a424a2e401a88e9e |
completed | May 2, 2026, 5:04 p.m. |
| PD | Predicate disambiguation | batch_69f62c1379f08190836c3e02b0c892df |
completed | May 2, 2026, 4:53 p.m. |
| PDg | Predicate description generation | batch_69f62d886828819080ec2f742b9449e3 |
completed | May 2, 2026, 4:59 p.m. |
Created at: April 26, 2026, 7:52 p.m.