Triple
T9574244
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hepzibah Pyncheon |
E231002
|
entity |
| Predicate | opensShopTo |
P89890
|
FINISHED |
| Object | support herself |
—
|
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: support herself | Statement: [Hepzibah Pyncheon, opensShopTo, support herself]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: opensShopTo Context triple: [Hepzibah Pyncheon, opensShopTo, support herself]
-
A.
openingTime
Indicates the time at which a place, service, or event begins operating or becomes accessible.
-
B.
openingSite
Indicates the location or site where an opening or access point is created, occurs, or is situated.
-
C.
openedFirstHypermarket
Indicates that the subject entity was the first to open a hypermarket for the object entity or within the context specified.
-
D.
opens
Indicates that one entity causes or allows another entity (such as an object, space, or resource) to become accessible or no longer closed.
-
E.
opensOn
Indicates that an entity begins operating, becomes accessible, or starts being available at a specified time or on a specified date.
- 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_69ca848091c48190bc313d6620d09555 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd99a94c788190a4bb5d2b676908ac |
completed | April 1, 2026, 10:18 p.m. |
| PD | Predicate disambiguation | batch_69ccd59b960c8190966a8870a2426bd5 |
completed | April 1, 2026, 8:21 a.m. |
| PDg | Predicate description generation | batch_69ccd93e90048190a2b0d7c5c195ba98 |
completed | April 1, 2026, 8:37 a.m. |
Created at: March 30, 2026, 8:05 p.m.