Triple
T26829371
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mrs. Otis |
E675455
|
entity |
| Predicate | offersProductToGhost |
P10882
|
FINISHED |
| Object | Tammany Rising Sun Lubricator |
—
|
NE NERFINISHED |
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: Tammany Rising Sun Lubricator | Statement: [Mrs. Otis, offersProductToGhost, Tammany Rising Sun Lubricator]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: offersProductToGhost Context triple: [Mrs. Otis, offersProductToGhost, Tammany Rising Sun Lubricator]
-
A.
offersServiceTo
Indicates that one entity provides or makes a service available for the benefit or use of another entity.
-
B.
offersServiceOn
Indicates that one entity provides or makes a service available on, during, or through another entity (such as a platform, date, or location).
-
C.
offersProduct
chosen
Indicates that one entity makes a product available to another entity, typically for sale or use.
-
D.
offersObject
Indicates that a subject provides or makes available a specific object to another party as an offer.
-
E.
offersLimitedServiceOn
Indicates that one entity provides a restricted, partial, or reduced version of a service to another entity, rather than full or regular service.
- 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_69eee9b776448190993a60b67fcc9545 |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69f727afd5d88190ad48735cd1b32787 |
completed | May 3, 2026, 10:47 a.m. |
| PD | Predicate disambiguation | batch_69f72737c42c8190a3f781a5e98868ff |
completed | May 3, 2026, 10:45 a.m. |
Created at: April 27, 2026, 5 a.m.