Triple
T28233826
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 白起 |
E711824
|
entity |
| Predicate | longestCampaignDirection |
P164141
|
FINISHED |
| Object | 向东攻韩魏赵 |
—
|
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: 向东攻韩魏赵 | Statement: [白起, longestCampaignDirection, 向东攻韩魏赵]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: longestCampaignDirection Context triple: [白起, longestCampaignDirection, 向东攻韩魏赵]
-
A.
longestCampaignDirection
chosen
Indicates the primary direction or orientation in which the longest campaign associated with an entity extends or progresses.
-
B.
notableCampaignDirection
Indicates that an entity played a significant role in directing or guiding a particular campaign.
-
C.
continuedCampaignsOf
Indicates that one campaign is a direct continuation or follow-up of another campaign, extending its efforts or objectives over time.
-
D.
campaignDirected
Indicates that a campaign is intentionally targeted or directed toward a specific entity or audience.
-
E.
conductedCampaignsAgainst
Indicates that an entity organized and carried out systematic efforts or operations targeting another entity in opposition or conflict.
- 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_69efb51ece308190b8c269a057e36652 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69f6438ba610819081543ffa43c5824c |
completed | May 2, 2026, 6:33 p.m. |
| PD | Predicate disambiguation | batch_69f641e0fde08190bf06a1c5b388aa84 |
completed | May 2, 2026, 6:26 p.m. |
Created at: April 27, 2026, 10:53 p.m.