Triple
T28233861
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Xi Shi |
E711825
|
entity |
| Predicate | hasCompanionInGroup |
P200515
|
FINISHED |
| Object | Wang Zhaojun |
—
|
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: Wang Zhaojun | Statement: [Xi Shi, hasCompanionInGroup, Wang Zhaojun]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCompanionInGroup Context triple: [Xi Shi, hasCompanionInGroup, Wang Zhaojun]
-
A.
hasCompanionRoleIn
Indicates that an entity serves in a companion or supporting role within a specified context, activity, or relationship.
-
B.
hasCompanionRoleTo
Indicates that one entity serves in a companion or supporting role in relation to another entity.
-
C.
hasCompanionCandidate
Indicates that an entity is associated with another entity that is being considered or proposed as a potential companion.
-
D.
hasCompanionColleague
Indicates that one entity has another entity as a colleague who also serves as a companion or close associate.
-
E.
hasCompanionIndex
Indicates that an entity is associated with a specific companion identified by an index or positional number within a set of companions.
- F. None of above. chosen
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_69efb51ece308190b8c269a057e36652 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69ff9361943c81909544203cbc998a69 |
completed | May 9, 2026, 8:04 p.m. |
| PD | Predicate disambiguation | batch_69ff913138a08190b59bdc9d8d199eb3 |
completed | May 9, 2026, 7:55 p.m. |
| PDg | Predicate description generation | batch_69ff935f48808190aa6f4834f59d45b8 |
completed | May 9, 2026, 8:04 p.m. |
Created at: April 27, 2026, 10:53 p.m.