Triple
T15314287
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Macedonian phalanx |
E366114
|
entity |
| Predicate | hasTypicalFrontage |
P118076
|
FINISHED |
| Object | variable according to tactical needs |
—
|
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: variable according to tactical needs | Statement: [Macedonian phalanx, hasTypicalFrontage, variable according to tactical needs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTypicalFrontage Context triple: [Macedonian phalanx, hasTypicalFrontage, variable according to tactical needs]
-
A.
streetFrontageOn
Indicates that a property or parcel directly borders or faces a particular street along at least one of its sides.
-
B.
hasBlackFrontDoor
Indicates that one entity possesses or features a front door whose color is black.
-
C.
frontType
Indicates the type or category of a front (e.g., boundary or leading side) that one entity presents or forms relative to another.
-
D.
hasFront
Indicates that an entity possesses or is associated with a front-facing side, surface, or portion.
-
E.
frontageMaterial
Indicates the material used on the exterior front-facing surface of a structure or property.
- 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_69d85a113ee881908e297a1d38dd79fa |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03dd050108190a584543cb93943a4 |
completed | April 16, 2026, 1:39 a.m. |
| PD | Predicate disambiguation | batch_69deca935e2c8190b640987ddfc542b9 |
completed | April 14, 2026, 11:15 p.m. |
| PDg | Predicate description generation | batch_69decf2e413481909d9180a8d78d2c17 |
completed | April 14, 2026, 11:35 p.m. |
Created at: April 10, 2026, 3:16 a.m.