Triple
T38481601
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wei Cheng |
E915690
|
entity |
| Predicate | relationToTaoCheng |
P204679
|
FINISHED |
| Object | father |
—
|
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: father | Statement: [Wei Cheng, relationToTaoCheng, father]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationToTaoCheng Context triple: [Wei Cheng, relationToTaoCheng, father]
-
A.
connectsTravelBetween
Indicates a relationship where something (such as a route, service, or mode of transport) enables or provides travel between two locations.
-
B.
relationshipToUsnavi
Indicates the type or nature of the relationship that an entity has with Usnavi.
-
C.
touristGatewayTo
Indicates a relationship where one place serves as the primary access point or entry hub for tourists visiting another place.
-
D.
touristAgency
Indicates that an entity is a travel or tourist agency that organizes or provides tourism-related services for another entity.
-
E.
isResortOf
Indicates that a location or facility functions as a resort associated with, belonging to, or serving a particular entity (such as a city, region, or organization).
- 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_69f76e8ff5cc8190a88803369183845e |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a037cae084081909004d77514c5f286 |
completed | May 12, 2026, 7:17 p.m. |
| PD | Predicate disambiguation | batch_6a037a1e32108190897356d6a7fed879 |
completed | May 12, 2026, 7:06 p.m. |
| PDg | Predicate description generation | batch_6a037c84ecbc81908232e5215355f43b |
completed | May 12, 2026, 7:16 p.m. |
Created at: May 3, 2026, 4:31 p.m.