Triple
T33878928
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sarah Reed |
E868430
|
entity |
| Predicate | promiseBroken |
P94334
|
FINISHED |
| Object | to treat Jane as her own children |
—
|
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: to treat Jane as her own children | Statement: [Sarah Reed, promiseBroken, to treat Jane as her own children]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: promiseBroken Context triple: [Sarah Reed, promiseBroken, to treat Jane as her own children]
-
A.
breaksPromiseAbout
chosen
Indicates that one entity fails to keep or honor a specific promise previously made to another entity regarding something.
-
B.
bondBroken
Indicates that a previously existing bond or connection between entities has been severed or is no longer intact.
-
C.
promiseMadeBy
Indicates that one entity has given a commitment or assurance to another entity to perform (or refrain from) a specific action or fulfill an obligation.
-
D.
brokenBy
Indicates that one entity causes the damage, destruction, or loss of functionality of another entity.
-
E.
brokeOathTo
Indicates that one entity violated or failed to honor a sworn promise or commitment made to another entity.
- 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_69f34995b81c8190acdb45cea5a10eff |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7051ad6e4819095e82bbd64761803 |
completed | May 3, 2026, 8:19 a.m. |
| PD | Predicate disambiguation | batch_69f700fe24e08190998e2c96fbaaad38 |
completed | May 3, 2026, 8:02 a.m. |
Created at: May 1, 2026, 1:48 a.m.