Triple
T36340008
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Young Marshal of Northeast China |
E894887
|
entity |
| Predicate | contrastsWithPerson |
P11289
|
FINISHED |
| Object | Zhang Zuolin |
E159987
|
NE 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: Zhang Zuolin | Statement: [Young Marshal of Northeast China, contrastsWithPerson, Zhang Zuolin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: contrastsWithPerson Context triple: [Young Marshal of Northeast China, contrastsWithPerson, Zhang Zuolin]
-
A.
providesContrastWith
Indicates that one entity is used to highlight differences or distinctions when compared with another entity.
-
B.
dramaticContrastWith
Indicates that one entity is presented in a way that sharply emphasizes differences in tone, style, or impact when compared with another entity.
-
C.
oftenContrastedWith
chosen
Indicates that one entity is frequently compared to another in a way that highlights their differences or opposing characteristics.
-
D.
characterContrast
Indicates a relationship where two characters are compared to highlight their opposing or significantly differing traits, roles, or behaviors.
-
E.
contrastedWithObject
Indicates that one entity is explicitly compared to another by highlighting their differences or opposing characteristics.
- F. None of above.
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_69f76e4e90148190b02fe52593c70b5b |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ff136ed2a881908f713401083970d1 |
completed | May 9, 2026, 10:58 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a39f8f759248190baf7bb78e372a8ad |
completed | June 23, 2026, 3:09 a.m. |
| PD | Predicate disambiguation | batch_69ff10f9e3448190b6cb6ea5a67713c1 |
completed | May 9, 2026, 10:48 a.m. |
Created at: May 3, 2026, 4:09 p.m.