Triple
T5091206
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Human Rights Watch |
E114754
|
entity |
| Predicate | roleOfKeyPerson |
P256
|
FINISHED |
| Object | executive director |
—
|
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: executive director | Statement: [Human Rights Watch, roleOfKeyPerson, executive director]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleOfKeyPerson Context triple: [Human Rights Watch, roleOfKeyPerson, executive director]
-
A.
keyPerson
chosen
Indicates that a person plays a primary, central, or critically important role in relation to an organization, project, or entity.
-
B.
namedPersonRole
Indicates that a person is identified by name as holding a specific role or position in a given context.
-
C.
roleCharacteristic
Indicates that a particular characteristic, quality, or attribute is associated with and helps define a given role or function.
-
D.
roleInText
Indicates that an entity participates in a text with a specific function or capacity (e.g., author, editor, character).
-
E.
roleInOperation
Indicates that an entity holds a specific function, duty, or position within a particular operation or activity.
- 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_69bd443e941881908eb4e8c685b6f656 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd7541b2bc8190b58c2a23733b7825 |
completed | March 20, 2026, 4:26 p.m. |
| PD | Predicate disambiguation | batch_69bd715c0a448190afc837c6c31dc6ab |
completed | March 20, 2026, 4:10 p.m. |
Created at: March 20, 2026, 1:40 p.m.