Triple
T33158014
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Li Jue |
E848637
|
entity |
| Predicate | heldHostage |
P48966
|
FINISHED |
| Object | Emperor Xian of Han |
—
|
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: Emperor Xian of Han | Statement: [Li Jue, heldHostage, Emperor Xian of Han]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heldHostage Context triple: [Li Jue, heldHostage, Emperor Xian of Han]
-
A.
heldHostagesFor
Indicates that one party unlawfully detained another party or parties as hostages for a period of time, typically to exert pressure or gain leverage.
-
B.
takesHostageDuring
Indicates that one entity seizes and holds another entity as a hostage in the course of a particular event or action.
-
C.
hostages
chosen
Indicates that one party is forcibly holding another party captive, typically to compel a third party to meet certain demands or conditions.
-
D.
wasHostageIn
Indicates that an entity was held as a hostage at or within a specified place or context.
-
E.
hostagePower
Indicates that one entity exerts power or leverage over another by holding someone or something important to that other entity as a hostage.
- 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_69f3495b02d08190bb3d366823dffc21 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6dd3cc0648190a275812d6711275a |
completed | May 3, 2026, 5:29 a.m. |
| PD | Predicate disambiguation | batch_69f6d82eaee081908f06a71546315aea |
completed | May 3, 2026, 5:07 a.m. |
Created at: May 1, 2026, 1:28 a.m.