Triple
T32552009
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bird Cloud: A Memoir |
E831999
|
entity |
| Predicate | hasSubjectPropertyName |
P198967
|
FINISHED |
| Object |
Bird Cloud
Bird Cloud is Annie Proulx’s remote Wyoming property that serves as the setting and central subject of her memoir "Bird Cloud: A Memoir."
|
E2013336
|
NE FINISHED |
How this triple was built (3 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: Bird Cloud | Statement: [Bird Cloud: A Memoir, hasSubjectPropertyName, Bird Cloud]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Bird Cloud Triple: [Bird Cloud: A Memoir, hasSubjectPropertyName, Bird Cloud]
Generated description
Bird Cloud is Annie Proulx’s remote Wyoming property that serves as the setting and central subject of her memoir "Bird Cloud: A Memoir."
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSubjectPropertyName Context triple: [Bird Cloud: A Memoir, hasSubjectPropertyName, Bird Cloud]
-
A.
hasSubproperty
Indicates that one property is a more specific version of another property, inheriting its meaning and constraints.
-
B.
hasSubjectPosition
Indicates that an entity occupies or is assigned to a particular subject role or position within a structure, context, or organization.
-
C.
hasSubjectState
Indicates that an entity (typically an event, statement, or situation) is associated with a particular state or condition of its subject.
-
D.
haveProperty
Indicates that an entity possesses, exhibits, or is characterized by a particular property or attribute.
-
E.
hasSubjectEntriesIn
Indicates that a subject is recorded or represented within specific entries of a collection, dataset, or catalog.
- F. None of above. chosen
Provenance (7 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_69f34925fd08819084cfe4ec566cb704 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69ff17be6ad48190963206f2619b1b28 |
completed | May 9, 2026, 11:17 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a347b8aa23481908beb80d7dbe8a1f2 |
completed | June 18, 2026, 11:13 p.m. |
| NEDg | Description generation | batch_6a347de3dd5881908008ee4889cf2f26 |
completed | June 18, 2026, 11:23 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a347e5fd94c819098a9b25f72882dea |
completed | June 18, 2026, 11:25 p.m. |
| PD | Predicate disambiguation | batch_69ff1724ba24819092c928fcbcb286ec |
completed | May 9, 2026, 11:14 a.m. |
| PDg | Predicate description generation | batch_69ff17bda59c8190b27c524f3e01c6df |
completed | May 9, 2026, 11:17 a.m. |
Created at: May 1, 2026, 1:02 a.m.