Triple
T28719547
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Poliorcetes |
E730052
|
entity |
| Predicate | notableWeaponType |
P16410
|
FINISHED |
| Object | Helepolis (siege tower) |
—
|
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: Helepolis (siege tower) | Statement: [Poliorcetes, notableWeaponType, Helepolis (siege tower)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableWeaponType Context triple: [Poliorcetes, notableWeaponType, Helepolis (siege tower)]
-
A.
typicalWeapon
Indicates that the object is a weapon commonly or characteristically used by the subject.
-
B.
featuredWeapon
Indicates that a particular weapon is highlighted or prominently showcased in relation to an entity, such as a character, event, or context.
-
C.
weaponCategory
chosen
Indicates the classification or type of weapon to which an item or armament belongs.
-
D.
symbolicWeapon
Indicates a relationship where something functions as a symbolic or emblematic weapon for an entity, representing power, threat, or conflict rather than serving as a literal physical armament.
-
E.
weaponForgedFor
Indicates that a weapon was specifically created or crafted for a particular entity, purpose, or context.
- 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_69f043e91fe48190b73bcd8e08d433e0 |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_6a0174e8b5b481908bf0c6d3d5b0f3b6 |
completed | May 11, 2026, 6:19 a.m. |
| PD | Predicate disambiguation | batch_6a01748d65248190ac3d9adfa9d0b274 |
completed | May 11, 2026, 6:17 a.m. |
Created at: April 28, 2026, 5:52 a.m.