Triple
T33632353
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ash Morgan |
E861598
|
entity |
| Predicate | roleInCons |
P202547
|
FINISHED |
| Object | technical specialist |
—
|
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: technical specialist | Statement: [Ash Morgan, roleInCons, technical specialist]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInCons Context triple: [Ash Morgan, roleInCons, technical specialist]
-
A.
roleInvolves
Indicates that a particular role includes or requires participation in a specified activity, responsibility, or function.
-
B.
roleInTheWay
Indicates that one entity is obstructing, hindering, or otherwise blocking another entity’s progress, action, or intended path.
-
C.
roleInActs
Indicates the specific function or character that an entity performs or portrays within one or more acts or performances.
-
D.
roleAccordingTo
Indicates that an entity holds a particular role or function as defined or interpreted by a specified source or perspective.
-
E.
roleInText
Indicates that an entity participates in a text with a specific function or capacity (e.g., author, editor, character).
- 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_69f34981c54c81909b33c3fa2208a52d |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a008ebb22408190a2293bced40a7e53 |
completed | May 10, 2026, 1:57 p.m. |
| PD | Predicate disambiguation | batch_6a008e8715dc8190ab23292605901bf4 |
completed | May 10, 2026, 1:56 p.m. |
| PDg | Predicate description generation | batch_6a008eba6de8819083165152448f6071 |
completed | May 10, 2026, 1:57 p.m. |
Created at: May 1, 2026, 1:41 a.m.