Triple
T32688809
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tianji |
E835799
|
entity |
| Predicate | associatedRulerPosthumousTitle |
P110011
|
FINISHED |
| Object |
Sun Hao, Marquis of Wuxing
Sun Hao, Marquis of Wuxing, was the last emperor of Eastern Wu during China’s Three Kingdoms period, later demoted to a marquis after his state’s conquest by the Jin dynasty.
|
E2133093
|
NE FINISHED |
How this triple was built (3 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: Sun Hao, Marquis of Wuxing | Statement: [Tianji, associatedRulerPosthumousTitle, Sun Hao, Marquis of Wuxing]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Sun Hao, Marquis of Wuxing Triple: [Tianji, associatedRulerPosthumousTitle, Sun Hao, Marquis of Wuxing]
Generated description
Sun Hao, Marquis of Wuxing, was the last emperor of Eastern Wu during China’s Three Kingdoms period, later demoted to a marquis after his state’s conquest by the Jin dynasty.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedRulerPosthumousTitle Context triple: [Tianji, associatedRulerPosthumousTitle, Sun Hao, Marquis of Wuxing]
-
A.
posthumousTitleOf
chosen
Indicates that one entity is the honorary or formal title granted to another entity after that entity’s death.
-
B.
posthumousTitleGiver
Indicates a relationship where one entity confers or bestows a posthumous title upon another entity after their death.
-
C.
posthumousTitleIn
Indicates that an entity was granted a specific posthumous title within a particular jurisdiction, period, or context.
-
D.
namedAfterReignTitle
Indicates that something is named after the official title held by a ruler during their reign.
-
E.
posthumousTitleStatus
Indicates the status or condition of an honorary title that is granted to a person after their death.
- F. None of above.
Provenance (6 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_69f3493211388190993801216afbc2a7 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_6a037cad051c8190b28b354b89208574 |
completed | May 12, 2026, 7:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a380f8161708190a47f70dccdd9155f |
completed | June 21, 2026, 4:21 p.m. |
| NEDg | Description generation | batch_6a3810a299448190ba0080197e6417de |
completed | June 21, 2026, 4:26 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a3811ab6ed8819097a93f8022d9d284 |
completed | June 21, 2026, 4:30 p.m. |
| PD | Predicate disambiguation | batch_6a0379f0cbe481909b4b8fc6cbe297f0 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 1:09 a.m.