Triple
T33352229
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sixth Cavalry Regiment |
E853975
|
entity |
| Predicate | equipmentHistory |
P176535
|
FINISHED |
| Object | horses |
—
|
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: horses | Statement: [Sixth Cavalry Regiment, equipmentHistory, horses]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: equipmentHistory Context triple: [Sixth Cavalry Regiment, equipmentHistory, horses]
-
A.
serviceHistory
Indicates the record of past services, maintenance, or support actions that have been performed over time.
-
B.
ownershipHistory
Indicates the sequence of past and present owners associated with an entity over time.
-
C.
operationalHistory
Indicates the record of how something has been used, functioned, or operated over time, including its past activities and events.
-
D.
suspensionHistory
Indicates a record of past instances in which an entity was suspended, including when and possibly why those suspensions occurred.
-
E.
hasManufacturerHistory
Indicates that there exists a record of past and/or current manufacturers associated with an entity, capturing changes or continuity in who produced it over time.
- 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_69f3496acbc8819099fd0305ecc42080 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6e3156ea48190b604e414665ef351 |
completed | May 3, 2026, 5:54 a.m. |
| PD | Predicate disambiguation | batch_69f6de0b9ba48190887c9eb5d06a2e94 |
completed | May 3, 2026, 5:32 a.m. |
| PDg | Predicate description generation | batch_69f6e312d7fc819094dec41810f2585d |
completed | May 3, 2026, 5:54 a.m. |
Created at: May 1, 2026, 1:34 a.m.