Triple
T3578928
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fort Point National Historic Site |
E75753
|
entity |
| Predicate | hasNumberOfGunEmplacements |
P43153
|
FINISHED |
| Object | over 100 |
—
|
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: over 100 | Statement: [Fort Point National Historic Site, hasNumberOfGunEmplacements, over 100]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNumberOfGunEmplacements Context triple: [Fort Point National Historic Site, hasNumberOfGunEmplacements, over 100]
-
A.
numberOfMainBatteryGuns
Indicates the quantity of primary (main) battery guns that an entity, typically a warship or similar platform, is equipped with.
-
B.
hasTurrets
Indicates that an entity is equipped with or possesses one or more turrets.
-
C.
armamentStations
Indicates a relationship where specific locations or mounts on a platform (such as a vehicle, vessel, or structure) are designated for installing or carrying weapons or armaments.
-
D.
internalWeaponsBays
Indicates that an entity is equipped with weapons storage or launch systems housed within its internal structure rather than mounted externally.
-
E.
numberOfGuns
chosen
Indicates the quantity of guns associated with a given entity or situation.
- 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_69ad85d5e3008190bdfe0bacdd1f5a1b |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc0defe14819095a337a840e33300 |
completed | March 8, 2026, 6:33 p.m. |
| PD | Predicate disambiguation | batch_69adb83810c481909c645c08b978edc1 |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:21 p.m.