Triple
T28800751
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Empress He |
E727224
|
entity |
| Predicate | reignAsEmpressConsortOfSong |
P15466
|
FINISHED |
| Object | 960–976 |
—
|
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: 960–976 | Statement: [Empress He, reignAsEmpressConsortOfSong, 960–976]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reignAsEmpressConsortOfSong Context triple: [Empress He, reignAsEmpressConsortOfSong, 960–976]
-
A.
reignAsEmpress
Indicates that a person holds and exercises the supreme imperial authority in the role of empress over a realm or empire.
-
B.
reignAsEmpressConsortBegan
chosen
Indicates the point in time when an individual began their tenure or role as an empress consort.
-
C.
reignAsQueenConsort
Indicates that a person holds the position and performs the role of queen consort during the reign of a monarch.
-
D.
lastEmpressConsortOf
Indicates that one person was the final empress consort (last reigning emperor’s wife in title) of another person.
-
E.
realmAsEmpress
Indicates that an entity holds the position or role of empress over a specified realm or domain.
- 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_69f0319b7c44819085736bcc256185e6 |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f6c49627908190b3553474c7c3072b |
completed | May 3, 2026, 3:44 a.m. |
| PD | Predicate disambiguation | batch_69f6c3f23ae081909a52801266063a3c |
completed | May 3, 2026, 3:41 a.m. |
Created at: April 28, 2026, 6:27 a.m.