Triple
T11790580
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Palestine Post Office |
E280376
|
entity |
| Predicate | usedScriptOnStamps |
P101594
|
FINISHED |
| Object | Latin script |
—
|
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: Latin script | Statement: [Palestine Post Office, usedScriptOnStamps, Latin script]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedScriptOnStamps Context triple: [Palestine Post Office, usedScriptOnStamps, Latin script]
-
A.
scriptOnSeal
Indicates that written characters or inscriptions are present on the surface of a seal.
-
B.
hasScriptOnBanknotes
Indicates that a currency’s banknotes contain written or printed script on them.
-
C.
inscriptionUsedWith
Indicates that a particular inscription is employed together with, or in association with, another object, tool, or context in which it is applied or interpreted.
-
D.
scriptUsedOnCoins
Indicates that a particular writing system or script is used on the inscriptions appearing on coins.
-
E.
overprints
Indicates that one entity is printed or superimposed on top of another, partially or completely covering the underlying material or pattern.
- 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_69d6ab258b808190b1735835c841e3a4 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a588d2c881909783c2d678c2a474 |
completed | April 10, 2026, 7:23 a.m. |
| PD | Predicate disambiguation | batch_69d8a2491f048190853239bc05090bf4 |
completed | April 10, 2026, 7:10 a.m. |
| PDg | Predicate description generation | batch_69d8a43cc0c881909fed7cd759fe90b1 |
completed | April 10, 2026, 7:18 a.m. |
Created at: April 8, 2026, 9:42 p.m.