Triple
T28106582
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | People's Park (Shanghai) |
E710379
|
entity |
| Predicate | marriageMarketDay |
P174691
|
FINISHED |
| Object | Saturday |
—
|
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: Saturday | Statement: [People's Park (Shanghai), marriageMarketDay, Saturday]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: marriageMarketDay Context triple: [People's Park (Shanghai), marriageMarketDay, Saturday]
-
A.
marriesFor
Indicates that one entity enters into marriage with another entity specifically for a particular reason, motive, or benefit.
-
B.
destinedToMarry
Indicates that two entities are fated or predetermined to marry each other in the future.
-
C.
taskForMarriage
Indicates a relationship where an action or task is performed specifically for the purpose of facilitating, preparing for, or fulfilling a marriage.
-
D.
marries
Indicates that one entity enters into a legally or socially recognized marital union with another entity.
-
E.
marriagePattern
Indicates the typical form or structure of a marriage relationship, such as how partners are selected, organized, or related within a social or cultural system.
- 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_69ef9b71fdb081908b4a61cd7ff147c1 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f6c5b7e46081909975b05f7298cc0e |
completed | May 3, 2026, 3:49 a.m. |
| PD | Predicate disambiguation | batch_69f6c3f23ae081909a52801266063a3c |
completed | May 3, 2026, 3:41 a.m. |
| PDg | Predicate description generation | batch_69f6c49069e48190a3486b6254a6645b |
completed | May 3, 2026, 3:44 a.m. |
Created at: April 27, 2026, 9:08 p.m.