Triple
T26785865
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Isabella Garcia-Shapiro |
E670375
|
entity |
| Predicate | troopNumber |
P25202
|
FINISHED |
| Object | 46231 |
—
|
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: 46231 | Statement: [Isabella Garcia-Shapiro, troopNumber, 46231]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: troopNumber Context triple: [Isabella Garcia-Shapiro, troopNumber, 46231]
-
A.
regimentalNumber
Indicates the unique identifying number assigned to a member of a regiment, linking an individual to their specific regimental record.
-
B.
troopAccess
Indicates that one party is permitted to move, station, or operate military troops within the territory, facilities, or jurisdiction of another party.
-
C.
militaryFormationNumber
Indicates the specific numerical designation assigned to a military formation within an armed force.
-
D.
hasBattalionNumber
Indicates that an entity (such as a military unit) is associated with a specific battalion number identifier.
-
E.
teamNumber
chosen
Indicates the specific numeric identifier assigned to a team within a larger group or 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_69eeb31d45f8819089f52ebdbc556218 |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f6197fccd0819097d2a402003b05ab |
completed | May 2, 2026, 3:34 p.m. |
| PD | Predicate disambiguation | batch_69f611ad2eb48190ac1ed0090f13f7a9 |
completed | May 2, 2026, 3:01 p.m. |
Created at: April 27, 2026, 4:13 a.m.