Triple
T33687821
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 4th Battalion |
E863088
|
entity |
| Predicate | hasHistoricSubunit |
P8012
|
FINISHED |
| Object | Commander-in-Chief’s Guard |
—
|
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: Commander-in-Chief’s Guard | Statement: [4th Battalion, hasHistoricSubunit, Commander-in-Chief’s Guard]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHistoricSubunit Context triple: [4th Battalion, hasHistoricSubunit, Commander-in-Chief’s Guard]
-
A.
historicalSubunit
Indicates that one entity functioned as a subordinate or component part of another entity during a specific historical period, but is no longer in that role in the present.
-
B.
historicalSubunitToUnit
chosen
Indicates that one entity was historically a subunit, subdivision, or component of another larger entity.
-
C.
hasSubhistory
Indicates that one history or sequence of events is a component, segment, or nested part of another, larger history.
-
D.
hasHistoricalCountrySubdivision
Indicates that one entity was a territorial or administrative subdivision of a historical country.
-
E.
hasHistoricalSubstratum
Indicates that one entity is historically underlain or influenced by another, earlier cultural, linguistic, or structural layer.
- 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_69f3498662b48190904442c39df84fb7 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fedec693b08190b0f8bfdb921e0766 |
completed | May 9, 2026, 7:14 a.m. |
| PD | Predicate disambiguation | batch_69fede16c1d48190a20d8a9c5722c307 |
completed | May 9, 2026, 7:11 a.m. |
Created at: May 1, 2026, 1:43 a.m.