Triple
T14007181
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spartan navy |
E336979
|
entity |
| Predicate | initialStrength |
P112125
|
FINISHED |
| Object | small compared to Athenian navy |
—
|
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: small compared to Athenian navy | Statement: [Spartan navy, initialStrength, small compared to Athenian navy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: initialStrength Context triple: [Spartan navy, initialStrength, small compared to Athenian navy]
-
A.
estimatedStrength
Indicates that a value represents an approximate or inferred level, magnitude, or intensity of something rather than a precisely measured strength.
-
B.
secondaryStrength
Indicates a secondary or supporting level of strength or influence that complements a primary one in the relationship between entities.
-
C.
totalStrength
Indicates the overall magnitude or combined level of strength associated with an entity or group of entities.
-
D.
attackerStrength
Indicates the level or magnitude of power, force, or capability possessed by the attacking entity in a given interaction or scenario.
-
E.
initialStatus
Indicates the original or starting state assigned to an entity before any changes or updates occur.
- 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_69d81c645c5c8190b1fd16a285a1b78a |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2ed327d88190a53af5768468a8eb |
completed | April 14, 2026, 12:10 p.m. |
| PD | Predicate disambiguation | batch_69dd465dfbc4819090d8c61fd572d35f |
completed | April 13, 2026, 7:39 p.m. |
| PDg | Predicate description generation | batch_69de01ed2098819088ec45069f6f2609 |
completed | April 14, 2026, 8:59 a.m. |
Created at: April 9, 2026, 10:19 p.m.