Triple
T36522005
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NSWindow |
E900205
|
entity |
| Predicate | roleInCocoa |
P203502
|
FINISHED |
| Object | top-level window object |
—
|
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: top-level window object | Statement: [NSWindow, roleInCocoa, top-level window object]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInCocoa Context triple: [NSWindow, roleInCocoa, top-level window object]
-
A.
roleInCoco
Indicates that an entity serves a specific role or function within the context of the COCO dataset or framework.
-
B.
roleInCrostini
Indicates that an entity participates in a Crostini environment with a specific role or function.
-
C.
roleInReact
Indicates that an entity participates in a reaction with a specified functional or contextual role (e.g., reactant, product, catalyst, or regulator).
-
D.
roleInChickenfoot
Indicates that an entity participates in a game of Chickenfoot (a dominoes variant) in a specific role or capacity.
-
E.
roleInMATE
Indicates that an entity participates in a MATE (Modeling and Analysis of Telecommunication Systems) context with a specific functional or contextual role.
- 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_69f76e5eedb88190a393b8c623f71dd7 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a0191d96dc88190ac0823e534f9d704 |
completed | May 11, 2026, 8:22 a.m. |
| PD | Predicate disambiguation | batch_6a01908110448190a46442ffe4d15f5f |
completed | May 11, 2026, 8:17 a.m. |
| PDg | Predicate description generation | batch_6a0191d8cc888190859143c9e459653a |
completed | May 11, 2026, 8:22 a.m. |
Created at: May 3, 2026, 4:11 p.m.