Triple
T14648488
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Semaine sanglante |
E343915
|
entity |
| Predicate | hasMainBattlefield |
P39414
|
FINISHED |
| Object | quartiers de l’ouest de Paris |
—
|
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: quartiers de l’ouest de Paris | Statement: [Semaine sanglante, hasMainBattlefield, quartiers de l’ouest de Paris]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMainBattlefield Context triple: [Semaine sanglante, hasMainBattlefield, quartiers de l’ouest de Paris]
-
A.
mainBattle
Indicates that one battle is the primary or most significant engagement associated with a particular conflict, campaign, or entity.
-
B.
battlefieldOf
chosen
Indicates that a location is the site where a particular battle or military engagement took place.
-
C.
battledIn
Indicates that two or more entities engaged in a battle or conflict that took place at a specific location or during a particular event.
-
D.
hasSignificantBattle
Indicates that a major or decisive battle occurred involving the related entities.
-
E.
placeOfMainEngagement
Indicates the primary location where an entity carries out its main activities, operations, or engagements.
- 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_69d822e1a2cc81908e5bb93cf61ce3cc |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb4ed037c8190a87bf43f839fec05 |
completed | April 14, 2026, 9:43 p.m. |
| PD | Predicate disambiguation | batch_69de6576f0208190aa94d995e797ac38 |
completed | April 14, 2026, 4:04 p.m. |
Created at: April 10, 2026, 1:26 a.m.