Triple
T38135799
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Xinhai |
E952347
|
entity |
| Predicate | EarthlyBranch |
P154836
|
FINISHED |
| Object | Hai |
—
|
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: Hai | Statement: [Xinhai, EarthlyBranch, Hai]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: EarthlyBranch Context triple: [Xinhai, EarthlyBranch, Hai]
-
A.
livesOn
Indicates that one entity resides or has its home on or atop another entity (such as a surface, structure, or geographic feature).
-
B.
geologicalBranchOf
Indicates that one geological unit, feature, or formation is a subdivision or offshoot of a larger, parent geological entity within a hierarchical structure.
-
C.
associatedWithEarthlyBranchPinyin
chosen
Indicates a relationship where something is linked to, corresponds with, or is represented by the pinyin form of a specific Chinese earthly branch.
-
D.
Gelände
Indicates a relationship where something is located on, takes place in, or is associated with a specific area of land or terrain.
-
E.
earthlyBranchesCycleLength
Indicates the length of the repeating cycle formed by the sequence of earthly branches in a given calendrical or symbolic system.
- 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_69f76f09a7148190a4b91c0bacdc127a |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fcc42cbac48190b8d3e4c9ce140838 |
completed | May 7, 2026, 4:56 p.m. |
| PD | Predicate disambiguation | batch_69fcb0fc69c88190800453eb57a7e62c |
completed | May 7, 2026, 3:34 p.m. |
Created at: May 3, 2026, 4:21 p.m.