Triple
T30809906
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gerald Finzi |
E784614
|
entity |
| Predicate | setsTextOf |
P31721
|
FINISHED |
| Object | Thomas Hardy |
E60124
|
NE 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: Thomas Hardy | Statement: [Gerald Finzi, setsTextOf, Thomas Hardy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: setsTextOf Context triple: [Gerald Finzi, setsTextOf, Thomas Hardy]
-
A.
setTextsBy
Indicates that one entity assigns or updates text content that is associated with another entity.
-
B.
settingOfCoreText
Indicates that a location, time, or context serves as the primary setting in which the core text’s events or content take place.
-
C.
adoptsTextOf
Indicates that one entity formally takes over and uses the text or wording originally produced or issued by another entity.
-
D.
textBy
chosen
Indicates that a given text or written content was authored or produced by a particular entity.
-
E.
useText
Indicates that one entity employs or applies a specific text as a resource, tool, or content in performing an action or fulfilling a function.
- F. None of above.
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_69f224b4eda48190bd212ce4f3901e56 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f69063edbc81909e7735954aabee0b |
completed | May 3, 2026, 12:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a28bbdddd6081908e699bf4476615db |
completed | June 10, 2026, 1:20 a.m. |
| PD | Predicate disambiguation | batch_69f68b7d2794819092fef8a63f4f3de8 |
completed | May 2, 2026, 11:40 p.m. |
Created at: April 29, 2026, 8:43 p.m.